search-hierarchy
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): This skill is entirely instructional and does not include scripts, binaries, or configuration files that execute logic.
- [Indirect Prompt Injection] (SAFE): The skill guides the agent to process data from file searches, which is a standard data ingestion surface. 1. Ingestion points: Results from search tools like AST-grep, LEANN, and Grep (SKILL.md). 2. Boundary markers: Absent in this instructional file. 3. Capability inventory: Example commands illustrate use of external search and read tools (SKILL.md). 4. Sanitization: Not applicable to this documentation skill.
Audit Metadata