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

wrike

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @useclawlink/cli package from the NPM registry at runtime.
  • [COMMAND_EXECUTION]: All Wrike interactions are performed via shell commands using the ClawLink CLI (npx @useclawlink/cli), which handles authentication and data transfer.
  • [DATA_EXPOSURE]: The skill stores credentials locally in the user's home directory at ~/.clawlink/credentials.json. This is standard practice for CLI-based authentication but should be protected like any other configuration file.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Data enters the agent context through CLI commands like npx @useclawlink/cli run wrike which fetch task descriptions and project data.
  • Boundary markers: None explicitly defined in the provided CLI commands.
  • Capability inventory: The skill uses subprocess calls to execute the ClawLink CLI.
  • Sanitization: Not explicitly visible; the skill notes that users should be prompted for confirmation before write actions are performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — wrike