flow-work
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to act on external data sources which could contain malicious instructions.
- Ingestion points: The agent selects tasks from plan paths, descriptions, and coordinator task briefs as detailed in SKILL.md Phase 1.
- Boundary markers: No delimiters or explicit instructions to ignore embedded directives are provided for the ingested task data.
- Capability inventory: The skill utilizes browser interaction, real CLI invocations, and API integration checks for implementation and verification in Phase 3.
- Sanitization: The instructions do not specify any validation, filtering, or sanitization of the content found within external plans or briefs.
Audit Metadata