skill-check

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed as a developer utility for static analysis of SKILL.md files. It adheres to the principle of least privilege by only requesting read-only access through the 'Read Glob' tool and does not attempt to modify the file system or perform unauthorized network operations.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and analyze untrusted content from external files provided by the user.
  • Ingestion points: Reads target SKILL.md files from the local file system (e.g., in ~/.claude/skills/) for parsing and validation.
  • Boundary markers: The instructions lack explicit delimiters or specific 'ignore' directives to prevent the agent from inadvertently following instructions found within the data it is validating.
  • Capability inventory: The skill's capabilities are limited to reading file content and returning a structured validation report; it lacks write permissions, network access, or command execution tools.
  • Sanitization: Content is passed through structural and semantic validation rules to extract YAML frontmatter and evaluate text quality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 06:59 AM
Security Audit — agent-trust-hub — skill-check