grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted architectural plans and designs which may contain hidden instructions, while having access to powerful shell and file system tools.
- Ingestion points: Architectural plans, designs, or proposals provided by the user during the activation phase.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore commands embedded within the design documents.
- Capability inventory: The skill allows use of Read, Grep, Glob, Bash, Write, and Edit tools to interact with the environment.
- Sanitization: There is no explicit sanitization or validation logic for external content processing.
Audit Metadata