square-post
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied text for 'content optimization', which represents an indirect prompt injection surface. However, the impact is limited to the content of the post being sent to the Binance API and is a core part of the vendor-provided functionality.\n
- Ingestion points: User-provided message content via trigger phrases in README.md and SKILL.md.\n
- Boundary markers: None provided in the instruction templates.\n
- Capability inventory: Submits content via POST request to binance.com in SKILL.md.\n
- Sanitization: None described; the agent performs direct optimization and submission.\n- [DATA_EXFILTRATION]: The skill makes network requests to an official Binance API to perform its primary function.\n
- Evidence: Outbound POST requests are directed to https://www.binance.com/bapi/composite/v1/public/pgc/openApi/content/add. This is the official domain for the skill author and a well-known service, posing no exfiltration risk under normal operation.
Audit Metadata