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

replicate

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 official npm registry. This is a standard method for utilizing the vendor's integration tools.
  • [COMMAND_EXECUTION]: Shell commands are used to interact with the ClawLink CLI for logging in, connecting to Replicate, and running model predictions. These commands are necessary for the skill's primary functionality.
  • [CREDENTIALS_UNSAFE]: The documentation notes that credentials are stored locally at ~/.clawlink/credentials.json. This is standard practice for CLI-based authentication and is transparently disclosed to the user.
  • [DATA_EXFILTRATION]: The skill communicates with claw-link.dev to manage Replicate OAuth sessions and execute actions. This network activity is consistent with the service's purpose of providing browser-based authentication for AI agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — replicate