x-twitter-growth

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides a suite of Python tools (tweet_analyzer.py, thread_builder.py, growth_tracker.py) for analyzing social media metrics and structuring content. All scripts are self-contained and operate exclusively on local files.
  • [SAFE]: The analysis detected no hardcoded credentials, remote downloads, persistence mechanisms, or obfuscated content. The scripts use standard Python libraries for data processing and text manipulation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied CSV and text files, which constitutes a potential injection surface.
  • Ingestion points: scripts/growth_tracker.py (load_analytics function), scripts/thread_builder.py (load_content function), and scripts/tweet_analyzer.py (load_tweets function).
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded content within the input files.
  • Capability inventory: The tools are restricted to data analysis and console output. No network operations, file-writing capabilities, or subprocess executions are present in the code.
  • Sanitization: Input data is handled using standard csv.DictReader and json.loads methods with basic type validation for numeric fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 02:59 PM
Security Audit — agent-trust-hub — x-twitter-growth