hunt-websocket
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted external data such as source code and network captures, creating an attack surface for indirect prompt injection. This is mitigated by the skill's lack of automated execution and requirement for human oversight.
- Ingestion points: Instructions specify reading user-supplied source code and traffic captures.
- Boundary markers: The skill mandates a safety confirmation gate and advises the agent to remain read-only without explicit authorization.
- Capability inventory: No automated tools or scripts are bundled; the skill relies on the user to execute recommended commands.
- Sanitization: Guidance is provided to redact sensitive information from reports.- [SAFE]: The skill contains no malicious code, obfuscated payloads, or persistence mechanisms. Its offensive security focus is governed by explicit warnings and authorization requirements.
Audit Metadata