vibe-agents
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from local project documentation to generate new configuration files, creating a surface for indirect prompt injection.
- Ingestion points: Extracts context from
docs/PRD-*.mdanddocs/TechDesign-*.md. - Boundary markers: None present; the skill lacks delimiters or instructions to ignore commands within the source text.
- Capability inventory: Uses the
Writetool to create several files includingAGENTS.mdand tool-specific configurations. - Sanitization: None present; content from the documentation is interpolated directly into templates without validation.
Audit Metadata