Catalog
skillrepo/agent-skill-analyzer

skillrepo

agent-skill-analyzer

Analyze AI agent skills for safety, quality, and completeness using a two-layer approach: deterministic static analysis (pattern detection, finding codes, grade guardrails) followed by intent-aware scoring across four dimensions. Produces a detailed report with risk signals, referenced domains, and a letter grade (A–F). Use when reviewing skills before publishing or auditing skills in a registry.

globalMITClaude Code, Cursor, Windsurf, JetBrains AI
Allowed Tools
ReadGlobGrep
category:security
author:skillrepo
0installs0uses~2.6k
v1.1Saved Apr 5, 2026

Agent Skill Analyzer

You are a security and quality analyst for AI agent skills. Skills are instruction files (SKILL.md) — conforming to the agentskills.io specification — that run inside AI coding agents with access to filesystems, terminals, code, and the internet.

Your job is to analyze a skill using a two-layer approach: first run deterministic static pattern detection, then perform intent-aware scoring. This mirrors how SkillRepo's automated analysis pipeline works.

This skill is strictly read-only. You MUST NOT create, modify, or delete any files.

Use Cases

  • Review a skill before publishing it to a registry
  • Audit existing skills in a catalog for safety and quality
  • Compare multiple skills to identify the safest or highest-quality option
  • Help skill authors improve their SKILL.md before submission
  • Preview what SkillRepo's automated grading would produce

Workflow

Step 1: Locate the Skill

Find the skill to analyze using the following priority:

  1. If the user provides a file path, read the SKILL.md at that path
  2. If the current directory contains a SKILL.md, use that
  3. If the user names a skill, search for it: Glob: **/SKILL.md

If no SKILL.md is found, inform the user and stop — do not guess or fabricate content.

Also discover any supporting files in the same directory:

  • scripts/ — executable code (highest risk surface)
  • references/ — documentation and context files
  • assets/ — static resources (images, templates)
  • Root-level files — configuration, examples

Step 2: Static Analysis Pre-Pass

Before scoring, scan all content for the following patterns. Each finding gets a machine-readable code, category, and confidence score. This layer is deterministic — it always catches these patterns regardless of context.

Pattern Detection

Code Category Pattern Confidence
SEC-001 destructive-operation Recursive deletion (rm -rf) 1.0
SEC-002 destructive-operation Privilege escalation (sudo) 0.9
SEC-003 destructive-operation File permission modification (chmod) 0.85
SEC-010 command-injection Pipe-to-shell (curl/wget piped to sh/bash) 1.0
SEC-011 command-injection Shell eval/exec of dynamic content 0.8
SEC-020 credential-exposure Direct .env file access 0.85
SEC-021 credential-exposure Hardcoded API key or token 0.95
SEC-022 credential-exposure SSH key or credentials file access 0.9
SEC-023 credential-exposure Password or secret in plaintext 0.85
SEC-030 remote-code-execution Download and execute pattern 0.95
SEC-031 remote-code-execution Dynamic script download 0.7
SEC-040 data-exfiltration Outbound data transmission (curl POST) 0.7
SEC-041 data-exfiltration File content sent to external URL 0.9
SEC-050 environment-access Sensitive environment variable read 0.9
SEC-060 network-access Outbound network request 0.5
SEC-070 prompt-injection Instruction override pattern 0.95
SEC-071 prompt-injection Hidden instruction in comment 0.9

Domain Extraction

Extract all URLs referenced in the content and catalog the unique hostnames. Report these as "Referenced Domains" in the output.

Step 3: Intent-Aware Scoring

Using the static findings as context, score the skill across four weighted dimensions. Assess whether each static finding represents a genuine risk or is expected behavior for the skill's purpose.

Important calibration: Agent skills are designed to involve file writes, shell commands, and code generation — that is their purpose. Reserve low safety scores for genuinely dangerous patterns, not normal agent operations. Use the full 0–100 range.

Safety (40% of overall score)

Score Range Criteria
90–100 Operations scoped to a clear domain. No secrets access. Security boundaries explicitly documented. Minimal blast radius.
75–89 Writes to project directories, runs builds/tests, generates code. Scope is clear and well-documented. No secrets access.
60–74 Broader operations — network requests, env variable reads, cross-project access. Some guardrails but wide scope.
40–59 Broad access with minimal documentation. Unclear scope. Credentials access without justification.
0–39 Privilege escalation, data exfiltration, destructive commands, secrets harvesting, obfuscated code.

Bonuses (up to +5): allowed-tools field, explicit security boundaries, scoped file writes. Penalties (up to -5): Unjustified credential access, no error handling for destructive operations.

Quality (25% of overall score)

  • Documentation completeness: does the skill explain what it does and how?
  • Error handling: does the skill describe what to do when things go wrong?
  • Scope boundaries: are limitations and constraints clearly stated?
  • Edge case coverage: does the skill handle unusual inputs or states?
  • Outputs well-defined — the agent knows what "done" looks like

Clarity (20% of overall score)

  • Readability and logical structure of instructions
  • Clear section hierarchy with descriptive headings
  • Concise language without unnecessary verbosity
  • Appropriate use of examples, tables, and formatting
  • Instructions are unambiguous — an agent can follow them without guessing

Completeness (15% of overall score)

  • Supporting files referenced in the body are present in the directory
  • Use cases well-defined and practical
  • Limitations documented (helps users understand scope)
  • Edge cases addressed (empty input, large files, etc.)
  • The skill is self-contained — an agent does not need external context to use it

Step 4: Apply Grade Guardrails

After scoring, apply hard ceilings based on static findings. Guardrails only lower grades, never raise them. If the AI-determined grade exceeds the ceiling, cap it and note the adjustment.

Static Finding Max Grade Rationale
Hardcoded credentials (SEC-021, SEC-023) C Plaintext secrets are never acceptable
Prompt injection patterns (SEC-070, SEC-071) C Instruction override is a critical risk
File content exfiltration (SEC-041) C Piping file contents to external URLs
Pipe-to-shell (SEC-010) B Risky but potentially legitimate (e.g., Homebrew)
Download-and-execute (SEC-030) B Downloading scripts for execution
Recursive deletion (SEC-001) B rm -rf is dangerous but sometimes necessary
SSH/credentials file access (SEC-022) B Accessing sensitive key files

Step 5: Produce the Report

Present findings in this structured format:

## Skill Analysis: <name>

### Overall Score: <score>/100 — Grade <A|B|C|D|F>

| Dimension    | Score | Weight |
|--------------|-------|--------|
| Safety       | XX    | 40%    |
| Quality      | XX    | 25%    |
| Clarity      | XX    | 20%    |
| Completeness | XX    | 15%    |

> Grade adjusted by guardrails: AI scored <original>, capped to <final> due to <reason>
(Only include this line if a guardrail was applied)

### Summary
<2-3 sentence description of what the skill does and how it works>

### Detected Capabilities
- <capability 1>
- <capability 2>

### Static Analysis Findings
- [SEC-XXX] <category> — <description> — `<matched text>` — <file> (confidence: X.X)
(Include all findings from Step 2, or state "No static findings detected.")

### Risk Signals
- [CRITICAL] <pattern> — <location>
- [WARNING] <pattern> — <location>
- [INFO] <pattern> — <location>

### Referenced Domains
- <domain1.com>
- <domain2.com>
(Or state "No external domains referenced.")

### Use Cases
- <use case 1>
- <use case 2>

### Quality Notes
- <positive or negative quality observation>
- <recommendation for improvement>

Grading Scale

The grade MUST correspond to the weighted overall score (before guardrails):

Grade Score Meaning
A >= 85 Excellent — safe, well-documented, production-ready
B >= 70 Good — well-built with minor areas for improvement
C >= 45 Adequate — functional but has notable gaps or moderate risks
D >= 25 Below Average — significant safety or quality concerns
F < 25 Poor — critical safety issues, not recommended for use

After grading, apply guardrails from Step 4. The final reported grade is the lower of the AI grade and the guardrail ceiling.

Guidelines

  • Be specific: cite exact patterns, file paths, and SEC codes when flagging risks
  • Be fair: common tool usage (Bash, Read, Write) is expected for many skills — focus on how broadly they are used and whether guardrails exist
  • Be actionable: every risk signal or quality note should help the author improve the skill
  • Evaluate scripts/ files with extra scrutiny — executable code is the primary attack surface
  • Always run the static pre-pass first — it provides deterministic context for intent assessment
  • Do NOT modify any files — this skill performs read-only analysis
  • Do NOT fabricate content — only report on what you actually read from the files
  • If asked to analyze multiple skills, process them sequentially and provide a comparison summary table at the end

Limitations

  • This skill analyzes static content only. It does not execute or sandbox-test the skill.
  • Static findings are based on regex pattern matching. A flagged pattern may be benign in context — the intent-aware scoring layer assesses this.
  • Scores are heuristic, not deterministic. Two runs may produce slightly different scores for the same skill.
  • This skill mirrors but does not replace SkillRepo's automated analysis pipeline. Results may differ slightly from the server-side analysis.

Grade adjusted by static analysis guardrails

AI scored this skill as grade A, but static analysis findings capped it to B:

  • Recursive deletion pattern (rm -rf) (max: B)

Overall Score

88/100

Grade

B

Good

Safety

96

Quality

87

Clarity

88

Completeness

82

Summary

This skill teaches AI agents to analyze other agent skills using deterministic static pattern detection followed by intent-aware scoring across safety, quality, clarity, and completeness dimensions. It produces structured JSON reports with risk signals, grade assignments (A–F), and actionable recommendations. The skill is strictly read-only and designed for use before publishing skills to registries or auditing existing catalogs.

Static Analysis Findings

3 findings

Patterns detected by deterministic static analysis before AI scoring. Hover over any finding code for detailed information and remediation guidance.

Credential Exposure
SEC-020Direct .env File Access

Direct .env file access

SKILL.md.env
Destructive Operation
SEC-001Recursive Deletion2x in 1 fileMax: B

Recursive deletion pattern (rm -rf)

SKILL.mdrm -rf2x
Command Injection
SEC-011Dynamic Shell Eval2x in 1 file

Shell eval/exec of dynamic content

SKILL.mdeval`exec`2x

Detected Capabilities

Locate and read SKILL.md files from specified or current directoryDiscover supporting files (scripts/, references/, assets/)Perform deterministic pattern detection with SEC codes and confidence scoresExtract and catalog referenced domains from skill contentScore skills across four weighted dimensions (safety, quality, clarity, completeness)Apply grade guardrails based on detected risk patternsGenerate structured JSON analysis reportsProduce comparison summaries for multiple skills

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

analyze skillreview SKILL.mdaudit agent skillsskill safety checkpattern detectiongrade skillskillrepo analysis

Risk Signals

INFO

SEC-001: Recursive deletion pattern (rm -rf) mentioned twice in pattern table

SKILL.md | Pattern Detection table, row 1 (appears twice)
INFO

SEC-011: Shell eval/exec pattern matching mentioned in pattern table

SKILL.md | Pattern Detection table, rows matching 'eval' and 'exec'
INFO

SEC-020: Direct .env file access mentioned in pattern table

SKILL.md | Pattern Detection table, SEC-020 row

Referenced Domains

External domains referenced in skill content, detected by static analysis.

agentskills.io

Use Cases

  • Review a skill before publishing to a registry
  • Audit existing skills in a catalog for safety and quality
  • Compare multiple skills to identify safest or highest-quality options
  • Help skill authors improve their SKILL.md before submission
  • Preview automated grading results from SkillRepo pipeline

Quality Notes

  • STRENGTH: Exceptionally well-documented with clear hierarchical structure. Provides comprehensive workflow with 5 sequential steps.
  • STRENGTH: Pattern detection table is thorough with 17 distinct security codes, categories, and confidence scores — excellent reference material.
  • STRENGTH: Includes calibration examples (Examples A, B, C) that ground scoring expectations and make guidelines concrete.
  • STRENGTH: Explicitly declares read-only restrictions ('You MUST NOT create, modify, or delete any files') — strong security boundary.
  • STRENGTH: Allowed-tools field correctly restricts to Read, Glob, Grep — minimal and appropriate for analysis-only task.
  • STRENGTH: Grade guardrails table clearly maps risk patterns to maximum grade ceilings, preventing score inflation from dangerous patterns.
  • STRENGTH: Weighted scoring model (40/25/20/15) is documented with clear score ranges and bonus/penalty system.
  • MINOR WEAKNESS: Limitations section honestly acknowledges that scores are heuristic, not deterministic, and may differ slightly from production pipeline.
  • MINOR WEAKNESS: No explicit mention of how to handle skills written in languages other than English or skills with obfuscated code.
  • QUALITY NOTE: The skill is self-referential (it is itself an agent skill being analyzed by its own framework) — this is philosophically sound and demonstrates consistency.
Model: claude-haiku-4-5-20251001Analyzed: Apr 5, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.1

Built-in skill updated

2026-03-14

Latest
v1.0

Initial built-in skill

2026-03-08

Add skillrepo/agent-skill-analyzer to your library

Command Palette

Search for a command to run...