bro
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to process and restate the 'last message', which is an untrusted data source. \n
- Ingestion points: The conversation's 'last message' is the primary input (SKILL.md). \n
- Boundary markers: No delimiters or explicit warnings are used to separate the input message from the skill's instructions. \n
- Capability inventory: The skill body and references/runtime.md mention high-privilege capability verbs including 'explore', 'implement', 'parallel', 'verify', and 'model_role'. \n
- Sanitization: There is no evidence of filtering, escaping, or validation of the input content before it is processed by the agent.
Audit Metadata