pp-kdpnichefinder

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and installs the kdpnichefinder-pp-cli and kdpnichefinder-pp-mcp binaries from the author's official GitHub repository (github.com/mvanhorn/printing-press-library) and the official NPM registry via the @mvanhorn/printing-press-library package.
  • [DATA_EXFILTRATION]: The skill includes functionality for external data transmission:
  • The --deliver webhook:<url> argument allows the agent to send command outputs, which may contain niche research results, to any user-specified external URL.
  • The feedback command can be configured to automatically send local usage notes to a remote server using the KDPNICHEFINDER_FEEDBACK_AUTO_SEND environment variable.
  • [COMMAND_EXECUTION]: The skill requires the Bash tool to perform software installation and to execute the core research CLI tool.
  • [PROMPT_INJECTION]: There is an indirect prompt injection surface through the processing of untrusted external content:
  • Ingestion points: Data is brought into the agent context via the niches, rank, and keywords commands which retrieve book titles and metadata from Amazon KDP buckets.
  • Boundary markers: None. The skill does not implement specific delimiters or 'ignore' instructions for data processed from the KDP source.
  • Capability inventory: The agent is equipped with the Bash tool, enabling shell command execution based on processed data.
  • Sanitization: No specific sanitization or filtering of the ingested book titles or metadata is described before output.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 10:45 AM
Security Audit — agent-trust-hub — pp-kdpnichefinder