wechat-compliance-redlines
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a shell command for querying local growth data using
tools/atoms_query.py. This is a standard project-local utility for data retrieval and does not involve network access or privilege escalation. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files (
growth-layers.approved.jsonl) and user-provided marketing schemes. - Ingestion points:
knowledge/04-atoms/growth-layers.approved.jsonland scheme descriptions. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: Shell execution of local Python scripts (
tools/atoms_query.py). - Sanitization: None mentioned in the skill instructions; assumed to be handled by the script implementation.
Audit Metadata