researchers-gov
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external government websites, including the DOJ, FBI, SEC, and CISA, using the
WebFetchandWebSearchtools. This behavior creates a surface area where instructions hidden in the external data could influence the agent's behavior. - Ingestion points: Data retrieved from official agency domains (e.g., justice.gov, fbi.gov, sec.gov) and historical archives (archive.org) via
WebFetchandWebSearchas specified inSKILL.mdandAGENCY_SOURCES.md. - Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate the external web content from the agent's core instructions.
- Capability inventory: The skill has access to
Write,Edit,Glob, andWebFetchtools. It does not have access to high-risk capabilities such as arbitrary shell command execution or persistence mechanisms. - Sanitization: There are no documented sanitization, filtering, or validation steps for the content retrieved from external sources before it is processed by the agent.
Audit Metadata