grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection vulnerability surface through its interaction with local codebase files.
- Ingestion points: The agent is instructed to explore the codebase and read specific documentation files, including CONTEXT.md, CONTEXT-MAP.md, and files within the docs/adr/ directory (SKILL.md).
- Boundary markers: The instructions do not include any delimiters or safety warnings to ensure the agent ignores potential instructions embedded within the data it reads from these files.
- Capability inventory: Across its operational flow, the skill has the capability to both read from the local filesystem and write updates to documentation files.
- Sanitization: Content ingested from the project's files is used directly without validation or sanitization to prevent the execution of malicious embedded prompts.
Audit Metadata