grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to explore the codebase and examine existing components, styles, or design tokens to answer questions. This ingestion of untrusted data from the project environment presents an indirect injection surface.
- Ingestion points: Instructions in SKILL.md direct the agent to read the local codebase and project components.
- Boundary markers: Absent. There are no delimiters or instructions provided to differentiate between the agent's operational logic and content found within the explored files.
- Capability inventory: The skill relies on file system read access to analyze the project codebase.
- Sanitization: There is no sanitization or filtering of instructions that might be embedded within the source code or design tokens being reviewed.
Audit Metadata