hunt-ssrf
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides methodologies for an agent to crawl and analyze untrusted external data (such as JavaScript bundles, API responses, and URL-fetching features), which could contain malicious instructions targeting the agent.
- Ingestion points: The skill maps multiple attack surfaces where external data enters the context, including URL parameters, HTTP response headers, and source code review (
SKILL.md). - Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between its core instructions and data fetched from external sources.
- Capability inventory: The skill encourages active probing of external and internal network endpoints using tools like curl and fetch operations.
- Sanitization: The instructions lack guidance on sanitizing or validating external content before the agent processes or reflects it in its analysis.
Audit Metadata