pp-fred
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install the
fred-pp-clibinary usingnpx -y @mvanhorn/printing-press-libraryorgo install github.com/mvanhorn/printing-press-library/library/other/fred/cmd/fred-pp-cli@latest. These resources are hosted on GitHub and NPM under the author's organization. - [COMMAND_EXECUTION]: The primary function of the skill is to execute the
fred-pp-clibinary with various arguments to interact with the FRED API and manage a local SQLite database. - [DATA_EXFILTRATION]: The tool includes a
--deliver webhook:<url>flag which allows the command output to be POSTed to any arbitrary external URL. Additionally, afeedbackfeature can be configured via environment variables (FRED_FEEDBACK_ENDPOINT) to send local notes to a remote server. - [INDIRECT_PROMPT_INJECTION]: The skill processes time-series data and metadata fetched from the external FRED API, which serves as an untrusted data source.
- Ingestion points: Data is ingested via
fred-pp-cli series observations,series search, and other API-connected subcommands (SKILL.md). - Boundary markers: None identified in the prompt instructions for the agent.
- Capability inventory: The tool can write to the local filesystem (
--deliver file:<path>) and perform network POST requests (--deliver webhook:<url>). - Sanitization: No specific sanitization or validation of the API data is mentioned before it is processed or displayed by the agent.
Audit Metadata