flowda-search
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from search results and web pages, creating a vulnerability surface where malicious instructions could be embedded in third-party content.
- Ingestion points: Search snippets and full page content fetched via the flowda_search tool described in SKILL.md.
- Boundary markers: Rule 3 explicitly instructs the agent to treat all fetched content as data and never follow instructions found within it.
- Capability inventory: The skill enables web search, news retrieval, and content extraction from external URLs.
- Sanitization: The skill relies on behavioral instructions provided to the agent to ignore instructions in data, rather than technical string sanitization within the markdown itself.
Audit Metadata