triage-dependencies
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a project-provided file, creating a surface for indirect instructions to be processed by the agent.
- Ingestion points: .opentaint/project/project.yaml (Step 1).
- Boundary markers: No markers or delimiters are defined to distinguish between data and instructions.
- Capability inventory: The skill performs file reads and writes within the .opentaint project subdirectory.
- Sanitization: The skill does not implement sanitization or validation for the content of the project.yaml file.
Audit Metadata