pp-govspend
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the
govspend-pp-clitool usingnpxfrom the@mvanhorn/printing-press-librarypackage on NPM. - [EXTERNAL_DOWNLOADS]: The skill includes a fallback installation method that fetches and builds the CLI tool directly from the vendor's GitHub repository using
go install github.com/mvanhorn/printing-press-library/library/other/govspend/cmd/govspend-pp-cli@latest. - [COMMAND_EXECUTION]: The skill is designed to execute the
govspend-pp-clibinary with various arguments to query federal award data and grant opportunities. - [INDIRECT_PROMPT_INJECTION]: The skill processes research results from external government sources (USAspending.gov, Grants.gov, and SAM.gov) which are then ingested into the agent's context.
- Ingestion points: Data enters the agent context through the output of the
govspend-pp-clitool, particularly when the--agentflag is used to emit structured JSON. - Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" warnings for the tool's output within the prompt.
- Capability inventory: The skill uses the
Read Bashtool to execute the CLI and manage its output as seen inSKILL.md. - Sanitization: There is no evidence of sanitization or filtering of the content returned from the external government APIs before it is presented to the agent.
Audit Metadata