pp-travelclick

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires downloading and installing the travelclick-pp-cli binary from the author's GitHub repository (github.com/mvanhorn/printing-press-library) or via a Node package (@mvanhorn/printing-press-library).
  • [COMMAND_EXECUTION]: The skill operates by executing shell commands using the local travelclick-pp-cli binary to search for hotel availability and manage local settings.
  • [DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> flag, which allows users or agents to POST command output to a remote URL, representing a data routing capability.
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a 'learning loop' via recall and teach commands that ingest user queries into a local SQLite database to synthesize command playbooks.
  • Ingestion points: User queries are captured and stored by the recall and teach commands in SKILL.md.
  • Boundary markers: The skill relies on instructions for the agent to manually strip PII; no automated delimiters or escaping for stored playbook logic are described.
  • Capability inventory: The skill can perform network API calls, write to a local database, and deliver data to external webhooks.
  • Sanitization: The documentation notes that the CLI scans for common email and phone patterns in queries but does not block them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 10:59 PM
Security Audit — agent-trust-hub — pp-travelclick