roast
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided plans and decisions to drive a fact-finding process. It directs the agent to autonomously explore the environment, creating a surface where malicious instructions within the user input could potentially influence tool use.
- Ingestion points: User input defining the plan, decision, or idea to be interrogated in SKILL.md.
- Boundary markers: The instructions lack explicit delimitation or warnings to ignore commands that might be embedded within the user's input.
- Capability inventory: The skill explicitly grants the agent the ability to 'dispatch a sub-agent' to query the 'filesystem, tools, etc.'
- Sanitization: There is no mention of validation, filtering, or sanitization of the user-provided context before it is used to guide environmental exploration.
- [EXTERNAL_DOWNLOADS]: The skill documentation mentions an external repository at
github.com/mattpocock/skillsas the source of its adaptation. This is an informative reference for attribution and does not involve automated downloading or execution of remote code.
Audit Metadata