negotiation
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads deal data from a project file to customize its advice.\n
- Ingestion points: .agents/sales-context.md (referenced in SKILL.md).\n
- Boundary markers: None present; the agent is not instructed to isolate this input.\n
- Capability inventory: The skill generates text and does not utilize shell, network, or file-write capabilities.\n
- Sanitization: No sanitization is performed on the ingested file data.\n- [SAFE]: No obfuscation, hardcoded credentials, or persistence mechanisms were detected. The skill is consistent with its intended purpose.
Audit Metadata