exec-plan
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface detected. The agent is directed to 'Read and follow' the file '.agents/workflows/exec-plan.md' step by step. If this file is under the control of an external actor, such as in a malicious repository, they could provide instructions that the agent would execute. Ingestion points: .agents/workflows/exec-plan.md. Boundary markers: Absent. Capability inventory: Full toolset associated with the agent. Sanitization: None.
- [SAFE]: No direct malicious patterns such as remote code execution, data exfiltration, or obfuscation were found in the skill content itself.
Audit Metadata