graft
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a guide for using the 'graft' CLI tool for repository analysis and context retrieval. No malicious instructions, obfuscation, or high-risk command patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for the agent to ingest and act upon repository content.
- Ingestion points: Repository source code and index nodes located in the graft/ directory.
- Boundary markers: Absent from the documentation.
- Capability inventory: The described toolset is limited to search and mapping operations (ask, grep, skeleton, callers, map) and lacks write or network permissions.
- Sanitization: Not explicitly mentioned in the instructions.
Audit Metadata