grilling
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and analyzes external codebases, files, and project documentation to settle design decisions automatically. This processing of untrusted project data creates a surface where hidden instructions in files could attempt to influence the agent's logic or the questions it presents to the user.
- Ingestion points: Accesses the local codebase, project files, and documentation in the environment.
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers when reading external content.
- Capability inventory: The skill logic provided does not include dangerous capabilities such as direct file writing, network exfiltration, or arbitrary shell command execution.
- Sanitization: No specific sanitization or filtering of the content retrieved from external files is described.
Audit Metadata