tk-grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security vulnerabilities were identified in the skill. Its functionality is limited to reading repository context and writing documentation files locally. The skill includes configuration to prevent implicit invocation, ensuring it only runs when explicitly requested by the user.\n- [PROMPT_INJECTION]: The skill ingests data from user-supplied plans, RFCs, or ideas and reads existing documentation files in the repository, which constitutes an attack surface for indirect prompt injection.\n
- Ingestion points: User-provided arguments (plans, tickets, RFCs) and local files (CONTEXT-MAP.md, CONTEXT.md, docs/adr/) as defined in SKILL.md.\n
- Boundary markers: Absent.\n
- Capability inventory: The skill has the capability to write new markdown files to the repository's documentation directory.\n
- Sanitization: Absent.\n While this ingestion surface exists, it is an inherent part of the skill's documentation purpose and is assessed as safe given the lack of dangerous capabilities like network access or arbitrary command execution.
Audit Metadata