usitc
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches tool configurations and Model Context Protocol (MCP) server definitions from
unbrowse.ai. - [INDIRECT_PROMPT_INJECTION]: The skill has a standard attack surface for indirect prompt injection as it processes external data from
usitc.govsearch results. - Ingestion points: Untrusted data enters the agent context via search results from
hts_usitc_gov__get_reststop_search(SKILL.md). - Boundary markers: No specific boundary delimiters or instructions to ignore embedded commands are present in the documentation.
- Capability inventory: The skill includes tools for web interaction and task execution, such as
unbrowse.runandunbrowse.scrape(SKILL.md). - Sanitization: There is no evidence of sanitization or filtering of the content received from the external site.
Audit Metadata