pp-table-reservation-goat

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install a CLI tool using npx -y @mvanhorn/printing-press, which fetches and executes code from the official NPM registry.
  • [COMMAND_EXECUTION]: The skill's operation relies on the execution of the table-reservation-goat-pp-cli binary through the shell to perform reservation queries and management.
  • [CREDENTIALS_UNSAFE]: The tool includes functionality (auth login --chrome) to import session cookies from the local Chrome browser profile to authenticate with OpenTable and Tock.
  • [DATA_EXFILTRATION]: The CLI tool features a --deliver webhook:<url> flag and a feedback command that allow command results and feedback notes to be sent to external network endpoints.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface:
  • Ingestion points: The agent processes data from external APIs (OpenTable, Tock, Resy) including restaurant names, descriptions, and location details.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within the external API responses.
  • Capability inventory: The agent can execute shell commands and interact with the local file system through the provided CLI tool.
  • Sanitization: There is no mentioned validation or sanitization of the content retrieved from external sources before it enters the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 11:53 AM
Security Audit — agent-trust-hub — pp-table-reservation-goat