writing-skills

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a bash script scripts/check.sh used for validating skill directories. The script uses standard system utilities (grep, awk, find, sed) to perform static analysis and optionally calls an external validator (skills-ref) if present in the environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to review other skills, which involves processing untrusted content. The documentation includes specific guidance for agents to detect security risks in the skills they audit, such as unauthorized network or filesystem access, which serves as a mitigation strategy during the review process.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 05:21 PM