bulletproof
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a process for executing shell commands to perform safe, non-mutating checks and recording the exact commands and outputs.
- [PROMPT_INJECTION]: The skill ingests untrusted data from external sources and claim sets during verification, which constitutes an indirect prompt injection surface. 1. Ingestion points: Claim sets, review artifacts, and primary external sources (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Command execution and file system access to artifacts directory (SKILL.md). 4. Sanitization: Absent.
Audit Metadata