classify-media-relevance

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions and heuristic rules for a classification task. It does not contain any executable code, scripts, or remote dependencies.
  • [SAFE]: No evidence of prompt injection, obfuscation, or persistence mechanisms was found in the provided content.
  • [SAFE]: The references to external domains (such as LinkedIn, Facebook, and Bing) are used strictly as examples for a tracking-domain blocklist, which is a standard safety feature for content extraction tools.
  • [SAFE]: While the skill processes untrusted data (alt text from web pages), the impact of any potential indirect prompt injection is minimal as the output is restricted to a structured classification decision with no access to dangerous tools.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 11:19 PM
Security Audit — agent-trust-hub — classify-media-relevance