test-idea-rewriting
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external test ideas, which could potentially contain malicious instructions intended to influence the agent's behavior during the transformation process.
- Ingestion points: Untrusted data enters the agent context via the
inputFileandinputDirparameters referenced in theAgent Integrationsection ofSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or instructions for the agent to ignore any embedded directives within the files being processed.
- Capability inventory: The skill uses agent capabilities to read from and write to the local file system as part of its batch and single-file transformation tasks.
- Sanitization: No specific sanitization, filtering, or escaping logic is defined for the external content before it is processed by the agent.
Audit Metadata