test-feature
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface through the ingestion of external data from application URLs and local specification files.
- Ingestion points: Data enters the agent context through the feature-description argument, local specification files, and content from the target application URL.
- Boundary markers: No explicit markers or instructions are used to separate ingested data from the agent's core instructions.
- Capability inventory: The skill possesses the ability to automate browser actions, capture screenshots and video, and write reports to the local file system.
- Sanitization: No sanitization or validation of the external content or specification files is performed prior to processing.
Audit Metadata