grilling
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to 'dispatch a sub-agent' to find facts from the environment, including the filesystem and tools, instead of asking the user. This establishes a surface where data retrieved from the environment could contain instructions that influence the agent's behavior during the reasoning process.
- Ingestion points: The agent is instructed to read from the filesystem and tool outputs in
SKILL.md. - Boundary markers: There are no instructions providing delimiters or warnings to ignore embedded instructions within the retrieved facts.
- Capability inventory: The skill explicitly leverages tool execution and filesystem access to gather environmental context.
- Sanitization: There is no evidence of sanitization or validation logic for the data retrieved from the environment.
Audit Metadata