skill-checker

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a bundled Python script (scripts/validate_skill.py) to automate structural checks on the targeted skill folder. The script uses standard libraries and performs read-only operations for analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (SKILL.md files and folder structures of other skills) for auditing purposes.
  • Ingestion points: Reads the contents of target skill folders and SKILL.md files through a validation script and direct agent observation as described in SKILL.md Phase 1 and 2.
  • Boundary markers: Absent. The skill does not explicitly use delimiters to separate the untrusted skill content from its own internal instructions during processing.
  • Capability inventory: Local file reading and script execution (scripts/validate_skill.py). The skill does not possess network access or arbitrary write capabilities.
  • Sanitization: The validation script uses regular expressions to parse content for patterns rather than executing or evaluating the content as code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:18 PM
Security Audit — agent-trust-hub — skill-checker