grimoire-test
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze source code and run test suites, creating a vulnerability surface for indirect prompt injection from untrusted external data.
- Ingestion points: The agent reads source code snapshots and processes the output of test execution commands (SKILL.md, references/batch-context.md).
- Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions embedded within the codebase being tested.
- Capability inventory: The skill has the capability to execute shell commands to run tests and perform file writes to fix test defects within authorized permissions (SKILL.md).
- Sanitization: There is no mention of sanitizing or escaping external content before the agent processes or acts upon it.
Audit Metadata