pp-booking-com

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the booking-com-pp-cli binary. It provides installation instructions using npx for the @mvanhorn/printing-press-library package and go install for the author's GitHub repository. Both sources are associated with the skill's author.
  • [COMMAND_EXECUTION]: The skill operates by executing shell commands via the booking-com-pp-cli binary. This is a core part of its functionality to interface with Booking.com and local storage.
  • [DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> flag, allowing users or the agent to POST command results to an external URL. Additionally, the feedback command can transmit data to a configured endpoint, which is disabled by default.
  • [PROMPT_INJECTION]: The skill processes external, untrusted content from Booking.com, such as hotel descriptions and customer reviews, which could potentially contain adversarial instructions.
  • Ingestion points: Data is ingested through commands like hotels list, hotels get, reviews, and search (SKILL.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands were identified in the prompt templates.
  • Capability inventory: The skill has the ability to execute shell commands and perform network requests via the CLI binary.
  • Sanitization: There is no evidence of sanitization or filtering for the retrieved external data before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 05:26 AM
Security Audit — agent-trust-hub — pp-booking-com