pp-rappi
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the rappi-pp-cli binary using npx from the @mvanhorn/printing-press-library npm package or via go install from the mvanhorn/printing-press-library GitHub repository. These resources are associated with the vendor providing the skill functionality.\n- [DATA_EXFILTRATION]: The rappi-pp-cli tool includes a --deliver webhook: flag that allows the agent to POST command results to an external URL. Additionally, a feedback command can be configured via environment variables (RAPPI_FEEDBACK_ENDPOINT) to transmit data to a remote server.\n- [COMMAND_EXECUTION]: The skill's primary function is to invoke the rappi-pp-cli binary to perform catalog operations. The installation process also involves executing shell commands like npx and go install.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from the Rappi Mexico catalog.\n
- Ingestion points: Catalog data retrieved via restaurants list-category, get, and list-city commands (SKILL.md).\n
- Boundary markers: No delimiters or instructions to ignore instructions embedded in catalog data are present.\n
- Capability inventory: The rappi-pp-cli tool can write results to local files or transmit them to external webhooks (SKILL.md).\n
- Sanitization: No sanitization of the retrieved catalog content is performed before processing.
Audit Metadata