ask-matt

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a router for natural language user input, which creates an attack surface for indirect instructions to influence agent behavior.
  • Ingestion points: User situational queries described in SKILL.md are used to determine which workflow to execute.
  • Boundary markers: No specific delimiters or instructions to ignore embedded data are mentioned in the routing logic.
  • Capability inventory: The skill references other tools capable of file system writes (/grill-with-docs), interactive script generation (/wizard), and network research (/research).
  • Sanitization: No sanitization or validation of user-provided situation descriptions is mentioned.
  • [DYNAMIC_EXECUTION]: The skill references a /wizard utility that generates interactive bash scripts to automate the collection and storage of environment variables and secrets into .env files and platform-specific secret stores.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 03:58 PM