bingx-announcement
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and displays content from the BingX announcement API, which represents an untrusted external data source that could contain malicious instructions.
- Ingestion points: Announcement titles, content summaries, and links are retrieved from the
/openApi/content/v1/announcementendpoint (specified inSKILL.mdandapi-reference.md). - Boundary markers: The skill lacks explicit instructions or delimiters (e.g., XML tags or clear 'ignore instructions' warnings) to prevent the agent from obeying commands that might be hidden inside the announcement text.
- Capability inventory: The skill is authorized to perform network read operations and has the capability to summarize and present data to the user.
- Sanitization: While the skill correctly instructs the agent to sanitize input parameters (rejecting
&,=,?,#, or newlines), it does not provide a mechanism to sanitize or escape the content returned by the API before it enters the agent's context.
Audit Metadata