scrapecreators

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network operations to external domains to retrieve social media data.
  • Evidence: manifest.json defines 12 steps involving GET and POST requests to catalog.selat.ai, stablesocial.dev, and clado.mpp.paywithlocus.com.
  • Content: User-supplied parameters such as handle, linkedinUrl, and hashtag are transmitted to these third-party endpoints.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from social media platforms which could contain malicious instructions.
  • Ingestion points: API responses from X/Twitter, LinkedIn, Instagram, and TikTok via the manifest.json steps.
  • Boundary markers: None identified in the manifest structure to delimit external content.
  • Capability inventory: The skill is configured for network reads via defined API endpoints.
  • Sanitization: No explicit sanitization or filtering of the retrieved social media content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:34 PM
Security Audit — agent-trust-hub — scrapecreators