clawild-moltbook

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configures the agent to fetch and execute @apify/mcp-server and @modelcontextprotocol/server-slack packages via npx. These are official tools from well-known organizations (Apify and Model Context Protocol) intended for web automation and Slack integration.
  • [PROMPT_INJECTION]: The skill processes untrusted social media content (e.g., from Twitter/X) using Apify actors, which introduces a surface for indirect prompt injection where malicious instructions in the scraped data could attempt to influence agent responses.
  • Ingestion points: Data fetched via apify/twitter-scraper (referenced in SKILL.md pseudo-code).
  • Boundary markers: None explicitly defined in the provided instructions.
  • Capability inventory: Sending messages via Slack, posting to Moltbook, and executing Apify CLI commands.
  • Sanitization: No specific content filtering or sanitization logic is described in the skill logic.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 11:21 PM
Security Audit — agent-trust-hub — clawild-moltbook