grilling
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided plans and ideas and may use sub-agents to retrieve data from the filesystem or other tools. This presents a potential surface for indirect prompt injection if the ingested data contains malicious instructions.
- Ingestion points: User input describing plans and environmental data retrieved by sub-agents in SKILL.md.
- Boundary markers: None specified in SKILL.md.
- Capability inventory: Filesystem and tool access via sub-agents in SKILL.md.
- Sanitization: None described.
Audit Metadata