social-publisher

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the socialclaw CLI package from the public NPM registry. This is the official tool required for the service's operation and is considered a safe dependency.
  • [COMMAND_EXECUTION]: Executes the socialclaw CLI for account list management and content publishing. These commands are standard for the tool's documented purpose and occur in response to user-triggered workflows.
  • [DATA_EXFILTRATION]: Performs network requests to getsocialclaw.com for API key validation and data synchronization. This activity is restricted to the legitimate service provider.
  • [PROMPT_INJECTION]: The skill processes data returned from the SocialClaw API, representing a standard indirect prompt injection surface for API-integrated tools. 1. Ingestion points: Data is ingested via 'socialclaw accounts list', 'socialclaw status', and 'socialclaw posts list' commands. 2. Boundary markers: None identified. 3. Capability inventory: Executes shell commands via the socialclaw CLI and curl. 4. Sanitization: None identified.
  • [CREDENTIALS_UNSAFE]: The setup instructions correctly guide users to use environment variables for the workspace API key rather than hardcoding credentials, following security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:12 PM
Security Audit — agent-trust-hub — social-publisher