xiong-an-due-diligence
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could potentially contain malicious instructions meant to influence the agent's behavior.
- Ingestion points: External data enters the agent context via the
web.search,web_fetch,patent.search, andpatent.fetchtools as described inSKILL.mdand initialized inscripts/run_due_diligence.py. - Boundary markers: The instructions do not define clear delimiters or use "ignore embedded instructions" warnings for the external content retrieved by these tools.
- Capability inventory: The agent has the ability to search the web, fetch patents, and write generated HTML reports to the local file system (using
scripts/run_due_diligence.py). - Sanitization: The skill lacks explicit sanitization or validation of the content retrieved from external URLs before it is rendered into the final HTML report.
Audit Metadata