security-threat-model
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyses external repository content, which presents a surface for potential indirect prompt injection attacks if malicious instructions are embedded in the codebase.
- Ingestion points: The agent reads all files within a user-specified repository path (
SKILL.md,references/prompt-template.md). - Boundary markers: The skill includes defensive instructions to ground architectural claims in specific 'Evidence anchors' and to separate runtime behavior from development/CI tooling.
- Capability inventory: The agent can read repository files and write a markdown report to the local filesystem.
- Sanitization: The skill explicitly mandates 'Security hygiene' in
references/prompt-template.md, requiring the redaction of all secrets, tokens, and keys found during analysis.
Audit Metadata