x-twitter-growth

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes several local Python scripts to perform its core tasks. Evidence: Commands like python3 scripts/profile_auditor.py, scripts/competitor_analyzer.py, and scripts/content_planner.py are executed with user-supplied arguments such as handles and topics.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection. 1. Ingestion points: Competitive intelligence Step 2 retrieves content from x.com via Brave search. 2. Boundary markers: There are no specific delimiters to isolate external content from the prompt context. 3. Capability inventory: The skill can execute local scripts via shell commands across its growth playbook. 4. Sanitization: No data validation or sanitization of retrieved external content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — x-twitter-growth