social-media-analyzer

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts, scripts/calculate_metrics.py and scripts/analyze_performance.py, to perform analytical tasks on social media datasets. This is a primary function of the skill.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection due to its processing of untrusted external data provided by the user.
  • Ingestion points: Social media campaign metrics and post content provided via input fields such as posts[].
  • Boundary markers: The instructions specify data validation for numerical metrics and dates, but do not provide explicit delimiters or instructions to isolate user-provided text from agent instructions.
  • Capability inventory: The skill utilizes subprocess calls to run Python scripts that analyze the provided datasets.
  • Sanitization: There is no documented evidence of string sanitization or input filtering for the social media content processed by the tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — social-media-analyzer