wechat-compliance-redlines

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions include a bash command to execute a local utility script python3 tools/atoms_query.py. This script is used to query growth atoms from an internal JSONL file and is considered a legitimate vendor-provided tool within the repository structure.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes external marketing solutions provided by users, which creates a surface for indirect prompt injection.
  • Ingestion points: Marketing schemes and the knowledge/04-atoms/growth-layers.approved.jsonl file.
  • Boundary markers: None specified in the instructions to isolate user-provided data.
  • Capability inventory: Execution of a local Python script (tools/atoms_query.py) that interacts with project data.
  • Sanitization: No input validation or sanitization routines are mentioned for the data being evaluated.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 02:02 AM
Security Audit — agent-trust-hub — wechat-compliance-redlines