searchis-query

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill executes npx @openduo/searchis, which downloads and runs a package from the NPM registry at runtime to facilitate document searching. \n- [COMMAND_EXECUTION]: The skill uses the Bash tool to perform CLI operations including service status checks, archive queries, and account activation. \n- [INDIRECT_PROMPT_INJECTION]: The skill processes internal research archives (transcripts and industry analyses) which are untrusted external inputs. \n
  • Ingestion points: Raw text from documents is ingested via the quote field in search results. \n
  • Boundary markers: The instructions state that the quote field contains 'exact text', but provide no delimiters or instructions to treat this content as purely data rather than instructions. \n
  • Capability inventory: The skill has access to the Bash tool, representing a potential execution path if instructions in the text are followed. \n
  • Sanitization: There is no description of content filtering or sanitization performed on the archival data before it is read by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:30 PM