execute-plan
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes and executes tasks defined in user-supplied plan files, which presents a surface for indirect prompt injection if the plan contains malicious instructions.
- Ingestion points: User-specified plan file content in SKILL.md.
- Boundary markers: Absent; the skill does not utilize delimiters or specific 'ignore' instructions for the plan content.
- Capability inventory: Execution of arbitrary tasks as defined in the plan to-do list, which may involve file system or environment changes across multiple files.
- Sanitization: Absent; the agent is instructed to directly 'Execute the to-do actions' without validation or filtering.
Audit Metadata