pp-hotel-goat

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions direct the installation of the hotel-goat-pp-cli binary via npx from the @mvanhorn NPM scope and go install from the mvanhorn GitHub organization.
  • [DATA_EXFILTRATION]: The CLI tool includes a --deliver webhook:<url> flag that enables sending the output of hotel searches and property details to an arbitrary external URL via an HTTP POST request. Additionally, a feedback mechanism can be configured to send local notes to a remote endpoint if specific environment variables are set.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external hotel listings and reviews via Google Hotels. 1. Ingestion points: Data returned by the hotels, hotel show, and hotel reviews commands in SKILL.md. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the command recipes. 3. Capability inventory: Execution of the hotel-goat-pp-cli binary, local file writing, and arbitrary network POST requests. 4. Sanitization: The skill does not specify any sanitization or validation logic for the ingested hotel data before it enters the agent's context.
  • [COMMAND_EXECUTION]: The skill instructions facilitate the execution of the hotel-goat-pp-cli binary using the Read Bash tool, where user-supplied parameters are passed as command-line arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 09:06 AM