recipe-task

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8).
  • Ingestion points: User-provided input in '$ARGUMENTS' is directly interpolated into the Agent tool prompt for the 'dev-workflows:rule-advisor' subagent in 'SKILL.md'.
  • Boundary markers: The input is not wrapped in delimiters or accompanied by instructions to treat the data as untrusted, which could allow instructions within the arguments to influence the subagent's behavior.
  • Capability inventory: The skill calls the 'dev-workflows:rule-advisor' subagent and manages execution via 'TaskCreate' and 'TaskUpdate' tools based on the subagent's output.
  • Sanitization: There is no evidence of validation or sanitization of the '$ARGUMENTS' content before it is processed by the subagent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 07:34 PM