grill-me
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is instructed to answer questions by researching the web, GitHub, and package source code. This involves ingesting untrusted data from external sources.
- Ingestion points: Web search tools, GitHub CLI/API, and package source code repositories mentioned in SKILL.md.
- Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions within the researched content.
- Capability inventory: The skill uses
functions.request_user_inputand explores the local codebase based on its findings. - Sanitization: There is no explicit logic to sanitize or validate the content retrieved from external sources before processing it.
Audit Metadata