social-media-analyzer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The provided skill consists only of documentation and metadata. The mentioned scripts (calculate_metrics.py and analyze_performance.py) are missing from the submission, meaning no executable logic was analyzed.
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest external data (CSV, JSON, and text), which is a known vector for indirect prompt injection. However, no malicious patterns were identified in the documentation. Evidence: 1. Ingestion points: SKILL.md (Campaign data inputs). 2. Boundary markers: Absent. 3. Capability inventory: Metric calculation and performance analysis. 4. Sanitization: Not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:25 PM