social-media-analyzer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill ingests untrusted social media data. However, the risk is negligible as the skill lacks high-privilege capabilities such as network access, file writing, or command execution.
  • Ingestion points: calculate_metrics.py (via campaign_data).
  • Boundary markers: Absent.
  • Capability inventory: None detected across all scripts.
  • Sanitization: Data is processed via standard mathematical functions.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): No external dependencies or remote execution patterns were detected. The skill uses only Python standard library imports.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:12 PM