pp-vagaro

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the 'vagaro-pp-cli' tool from the author's NPM package (@mvanhorn/printing-press-library) or official GitHub repository (github.com/mvanhorn/printing-press-library). These are vendor-owned resources provided by mvanhorn to enable the skill's discovery and booking functionality.\n- [COMMAND_EXECUTION]: The skill operates by executing the 'vagaro-pp-cli' binary through the shell, allowing the agent to perform marketplace lookups and account management tasks.\n- [DATA_EXFILTRATION]: The CLI tool includes a '--deliver webhook:' feature, which is a documented functional capability allowing command output to be transmitted to an external endpoint. Additionally, the 'auth login --chrome' functionality facilitates the import of session cookies and JWTs from the user's browser for authentication purposes.\n- [PROMPT_INJECTION]: The skill processes external content from the Vagaro marketplace, such as business descriptions and reviews, which creates a surface for potential indirect prompt injection.\n
  • Ingestion points: The 'listings', 'business get', and 'business services' commands retrieve data from the external Vagaro marketplace.\n
  • Boundary markers: The skill instructions do not define specific delimiters or isolation protocols for handling the output of these tools.\n
  • Capability inventory: The skill possesses the ability to execute various subcommands of the 'vagaro-pp-cli' via Bash.\n
  • Sanitization: Data is retrieved and presented in a structured JSON format, though the field contents originate from untrusted marketplace providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 05:24 AM
Security Audit — agent-trust-hub — pp-vagaro