grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied plans or designs, creating a potential surface for indirect prompt injection where data could be interpreted as instructions.
- Ingestion points: The description in
SKILL.mdindicates the skill ingests external "plans or designs" to generate documentation. - Boundary markers: There are no specified delimiters or boundary instructions to separate analyzed content from the agent's task instructions.
- Capability inventory: The skill instructions involve calling tools (
grillinganddomain-modeling) and generating documentation files like ADRs and glossaries. - Sanitization: No explicit sanitization or filtering of the processed content is defined in the instructions.
- [NO_CODE]: The skill consists only of instructions and configuration files; it does not include any executable scripts, binaries, or source code files.
Audit Metadata