threat-model
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to perform a security baseline assessment and document it for the user. Its actions align with its description and do not involve unauthorized activities.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its analysis of repository content. 1. Ingestion points: The skill analyzes all repository files, entry points, and data stores (SKILL.md). 2. Boundary markers: None identified in the workflow or reference template. 3. Capability inventory: The skill has the capability to write to the local filesystem, specifically creating .agent-security/threat-model.md and .agent-security/security-config.json (SKILL.md). 4. Sanitization: There is no explicit sanitization step for the repository data being processed.
Audit Metadata