sensei-prove-it
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed of purely instructional Markdown and configuration data intended to guide AI behavior during code reviews.
- [SAFE]: Analysis of the skill body and metadata reveals no evidence of prompt injection attempts, data exfiltration, or obfuscation techniques.
- [SAFE]: The skill does not perform any network operations, file system modifications, or external code downloads.
- [PROMPT_INJECTION]: The skill acts as an interface for processing untrusted code and test files. While this is an indirect prompt injection surface, the risk is minimal as the skill does not have access to any external tools, network capabilities, or file system operations that could be exploited.
- Ingestion points: User-provided code and test files in
SKILL.md. - Boundary markers: None present.
- Capability inventory: No subprocess calls, network ops, or file writes across any files.
- Sanitization: None present.
Audit Metadata