pp-whoop

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the whoop-pp-cli binary using npx from the npm registry to fetch the @mvanhorn/printing-press package.
  • [COMMAND_EXECUTION]: The skill's primary operation involves executing the whoop-pp-cli binary with various flags to retrieve and manage fitness metrics.
  • [DATA_EXFILTRATION]: The CLI includes a --deliver webhook:<url> feature that enables routing command output to arbitrary network endpoints. While a functional feature for data integration, it allows the transmission of retrieved fitness data to external locations.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its ingestion of external data.
  • Ingestion points: Data is ingested from the Whoop API and local feedback logs located at ~/.whoop-pp-cli/feedback.jsonl.
  • Boundary markers: There are no specific instructions or delimiters used to separate untrusted external data from the agent's core instructions.
  • Capability inventory: The skill possesses command execution capabilities and network access via its webhook delivery system.
  • Sanitization: The skill does not describe any specific sanitization or validation of the data retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 09:41 PM