workflow-review
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests workflow files and execution evidence, which are external data sources that could potentially contain malicious instructions intended to influence the agent.
- Ingestion points: Reads workflow files and recent execution evidence as defined in SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the analyzed data.
- Capability inventory: The skill instructs the agent to run affected steps and tests based on the analyzed workflows.
- Sanitization: No sanitization or validation logic for the processed data is mentioned in the instructions.
Audit Metadata