grimoire-implement
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (conversations, tickets, specs, plans) to drive code implementation, creating a surface for indirect prompt injection.
- Ingestion points: Instructions in SKILL.md direct the agent to resolve outcomes from "supplied conversation, ticket, spec, or plan".
- Boundary markers: There are no defined delimiters or instructions to ignore malicious directives embedded within the processed external data.
- Capability inventory: The skill allows for file system modifications (creating diffs and new files) and verification checks (potentially involving code or test execution).
- Sanitization: The instructions do not specify any sanitization, filtering, or validation of the external input before it influences the agent's code generation logic.
Audit Metadata