patent-inventor-profile-report
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external patent and scholarly data from the PatSnap database, which constitutes a standard attack surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through MCP tool calls in Step 2 (patent lists) and Step 7 (academic papers) as defined in SKILL.md and references/data_collection_steps.md.
- Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions found within the retrieved patent titles, abstracts, or metadata.
- Capability inventory: The agent has the capability to execute patent search tools and write generated HTML reports to the @session/reports/ directory.
- Sanitization: There are no explicit instructions for sanitizing or escaping external content before incorporating it into the final HTML output or using it for inventor rating calculations.
Audit Metadata