social-media-analyzer

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted campaign data and post metadata to generate insights and recommendations, which establishes an indirect prompt injection surface where malicious instructions in the data could influence the agent's behavior.\n
  • Ingestion points: Post metadata and metrics ingested via the SocialMediaMetricsCalculator class in scripts/calculate_metrics.py and the PerformanceAnalyzer class in scripts/analyze_performance.py.\n
  • Boundary markers: The skill does not implement boundary markers or instructions to disregard potential commands embedded in the input data.\n
  • Capability inventory: Analysis of scripts/calculate_metrics.py and scripts/analyze_performance.py reveals no dangerous capabilities such as subprocess calls, dynamic code execution (exec/eval), filesystem modifications, or network operations.\n
  • Sanitization: No text-based sanitization or escaping is performed on fields like post_id or content_type; numerical safety is limited to a safe_divide function to prevent errors.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 11:10 PM