exec-plan

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill directs the agent to read and execute instructions from a specific local file path.
  • Ingestion points: .agents/workflows/exec-plan.md (SKILL.md)
  • Boundary markers: Absent; instructions are to be followed "step by step" without content isolation or delimiters.
  • Capability inventory: Instructions in the target file guide the agent through plan generation and management workflows, which could involve execution of arbitrary agent actions.
  • Sanitization: No sanitization, validation, or safety warnings are provided regarding the content of the external file before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 09:34 PM