discovery-eyes
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied sample messages and threads to simulate litigation discovery readings. This constitutes an ingestion point for untrusted data that could potentially contain malicious instructions aimed at the agent.
- Ingestion points: User-provided sample messages and threads as specified in the 'Required Inputs' section of SKILL.md.
- Boundary markers: The skill does not currently specify the use of delimiters or 'ignore' instructions when processing the provided sample content.
- Capability inventory: The skill has no capabilities to execute code, perform network requests, write to the file system, or call external tools. It is restricted to text-based analysis.
- Sanitization: The instructions do not define a process for sanitizing or escaping the content within the sample messages before analysis.
Audit Metadata