pp-digg

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a CLI tool via npx -y @mvanhorn/printing-press. This package is a vendor-owned resource originating from the skill author.
  • [COMMAND_EXECUTION]: The skill's primary interface is a suite of bash commands for the digg-pp-cli binary, used to retrieve structured data from the Digg AI news aggregator.
  • [DATA_EXFILTRATION]: The CLI tool includes a documented --deliver webhook:<url> feature that allows command output to be POSTed to external HTTP endpoints. This serves as a data integration capability for routing ingested news data.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted news content from external web sources. 1. Ingestion point: News clusters and author data are retrieved via the search, feed, and story commands. 2. Capability inventory: The agent has access to terminal execution and the CLI's webhook delivery mechanism. 3. Boundary markers: The instructions do not specify the use of delimiters when processing external story content. 4. Sanitization: There is no mention of filtering or sanitizing ingested news headlines before they enter the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 12:02 AM