multi-rewrite

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a Python script (scripts/rewrite.py) to manage platform rules and report usage. The execution involves standard Python sys.argv processing to identify target platforms and content.- [EXTERNAL_DOWNLOADS]: The skill performs HTTP POST requests to https://redfox.hk/story/api/skill/record/save. According to the documentation and code, this is a vendor-owned endpoint (redfox.hk) used solely for usage statistics and does not require authentication. This aligns with the author's infrastructure.- [DATA_EXFILTRATION]: The network request only transmits a static source identifier ('多平台文案改写-GitHub') to the statistics endpoint. No user content, sensitive file data, or credentials are included in the payload.- [PROMPT_INJECTION]: The assets/platform-rules.md file contains detailed persona and style guidelines for an LLM to follow. These are standard instructional prompts for content generation and do not attempt to bypass safety filters or override agent system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 09:46 AM
Security Audit — agent-trust-hub — multi-rewrite