recon-osint
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve fetching and analyzing data from external, third-party sources which introduces an indirect prompt injection surface.
- Ingestion points: Data is ingested via tools such as github-search, shodan, censys, and google-dorks from the public internet (SKILL.md).
- Boundary markers: The skill does not provide specific instructions to the agent to delimit or isolate this external data, increasing the risk of the agent following instructions hidden in search results.
- Capability inventory: The skill is configured to use tools that interact with web services and security APIs.
- Sanitization: There are no instructions for sanitizing or validating the content retrieved from these external sources before the agent processes it.
Audit Metadata