plan
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: This skill consists solely of markdown instructions. No scripts, binaries, or shell commands are included or referenced for execution.
- [PROMPT_INJECTION]: The skill directs the agent to follow a process defined in
.agents/workflows/plan.md. This represents a surface for indirect prompt injection (Category 8) as the agent is instructed to obey instructions from a data source. - Ingestion points: .agents/workflows/plan.md (referenced file)
- Boundary markers: None defined in the skill content.
- Capability inventory: No tool use or system capabilities are invoked in this file.
- Sanitization: No sanitization or validation of the workflow file's content is performed within this instruction.
Audit Metadata