skills/clawlink-hq/skills/wakatime/Gen Agent Trust Hub

wakatime

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch and execute the @useclawlink/cli package from the NPM registry, which is the core component for interacting with the WakaTime API.
  • [CREDENTIALS_UNSAFE]: The instructions note that credentials for the service are stored locally at ~/.clawlink/credentials.json. This is a tool-specific configuration path and represents standard local credential management for this type of CLI utility.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Natural language input is passed to the npx @useclawlink/cli actions wakatime command to search for relevant developer productivity actions (SKILL.md).
  • Boundary markers: The skill includes a clear instruction to "confirm with the user before any write," establishing a manual checkpoint for state-changing operations.
  • Capability inventory: The skill is capable of reading and updating WakaTime data via subprocess execution of the @useclawlink/cli tool (SKILL.md).
  • Sanitization: Input sanitization is handled by the underlying CLI tool, with additional safety provided by the requirement for explicit user confirmation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 05:45 PM