Back to skill

Security audit

Skill Linter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local SKILL.md linter/advisor with no evidence of hidden network access, persistence, exfiltration, or destructive behavior.

Install only if you want a SKILL.md-focused linter/advisor. It can read and potentially edit/write skill files when used by an agent, so review suggested changes before accepting them; the bundled CLI itself only reads the file path you provide and prints a report.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description is broadly phrased to trigger on generic review, creation, audit, or improvement requests for SKILL.md files, which can overlap with ordinary editing or review workflows. This increases the chance of unintended activation, causing the agent to apply this skill in situations where a narrower or more security-aware skill would be more appropriate.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · skill_linter.py (reported line 321)May include surrounding context.

python
def main():
    if len(sys.argv) < 2:
        print("用法: python3 skill_linter.py <SKILL.md 路径>")
        print("示例: python3 skill_linter.py ~/.claude/skills/my-skill/SKILL.md")
        sys.exit(1)

    filepath = sys.argv[1]

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The module and function docstrings present this as a SKILL.md checker, which implies analysis of the file even when some sections are malformed. However, the code only runs analyze_frontmatter and analyze_content when result.frontmatter is truthy, so files with missing or invalid frontmatter are not fully analyzed despite the stated intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains natural-language strings that force a specific language/locale for the skill's documentation and interaction. Under the policy, hard-coding a language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The manifest describes a skill for reviewing, creating, or improving SKILL.md files in a general sense. In practice, this implementation is a narrow command-line linter that reads one local file path and prints a report, which is a more limited behavior than the manifest suggests.

Content

No source excerpt is available for this finding.