pp-intervals-icu

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs binaries from github.com/mvanhorn/printing-press-library and the @mvanhorn/printing-press-library NPM scope using go install and npx during setup. These resources are owned by the skill author.
  • [DATA_EXFILTRATION]: The CLI provides a --deliver webhook:<url> feature that allows it to transmit training data results and activity summaries to external remote servers.
  • [CREDENTIALS_UNSAFE]: The documentation instructs users to manage and store their INTERVALS_ICU_API_KEY in environment variables or in a local configuration file located at ~/.config/intervals-icu-pp-cli/config.toml.
  • [COMMAND_EXECUTION]: The skill executes shell-based installation routines and various CLI commands through the intervals-icu-pp-cli binary.
  • [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection (Category 8) as it processes external data from the intervals.icu API.
  • Ingestion points: The intervals.icu REST API (fetching activities, wellness trends, calendar, and workout data into a local SQLite database).
  • Boundary markers: Absent.
  • Capability inventory: Network operations (webhooks, API requests), File system writes (local SQLite database, configuration files, feedback logs), Subprocess execution (all primary CLI commands).
  • Sanitization: Not specified for the ingested API content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 10:59 PM
Security Audit — agent-trust-hub — pp-intervals-icu