regex-mastery
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes instructions for the agent to execute an
lscommand to verify the installation of recommended companion skills in specific local directories.\n- [EXTERNAL_DOWNLOADS]: The skill recommends installing additional companion skills from the vendor's repository using thenpxcommand.\n- [PROMPT_INJECTION]: The skill contains a role-play instruction directing the agent to start responses with a specific emoji (🧢).\n- [PROMPT_INJECTION]: The skill's primary function involves processing untrusted user input for regex matching, which is a surface for indirect prompt injection. The skill mitigates this by providing specific defensive guidelines against catastrophic backtracking (ReDoS).\n - Ingestion points: User-supplied text and patterns (SKILL.md).\n
- Boundary markers: Absent.\n
- Capability inventory: Filesystem listing (
ls) and suggested shell commands (npx).\n - Sanitization: Extensive guidance and examples on safe regex construction and backtracking prevention.
Audit Metadata