bkit-explore
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and renders metadata from local files, providing a surface for indirect prompt injection. 1. Ingestion points: Reads from skills//SKILL.md and agents/.md files. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded content are defined in the output layout. 3. Capability inventory: The skill uses Read, Glob, and Grep tools to perform filesystem scans. 4. Sanitization: No sanitization or validation of the extracted text is mentioned in the security or behavior sections.
Audit Metadata