recohere
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local environment to drive its decision-making process for refactoring, which constitutes a potential vulnerability surface. * Ingestion points: The agent reads git log history, the spec/glossary.md file, and architectural decision records (ADRs) to rank refactoring candidates (SKILL.md). * Boundary markers: The instructions lack explicit delimiters or safety instructions to prevent the agent from following malicious commands that could be embedded in commit messages or documentation. * Capability inventory: The skill performs codebase searches using grep, writes reports to the local .scratch/ directory, and instructs the agent to initiate code migrations using the /write-spec tool (SKILL.md). * Sanitization: There is no evidence of sanitization or validation of the data retrieved from the project history or documentation files before it is processed.
Audit Metadata