moomoo-news-search
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the use of shell commands such as
curlto interact with its backend API, as specified in the workflow and binary requirements. - [EXTERNAL_DOWNLOADS]: The skill performs network requests to
https://ai-news-search.moomoo.com. This domain is associated with moomoo, a well-known financial services provider, and the operations involve fetching public news data. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from an external API.
- Ingestion points: News content (titles, URLs) is fetched from the moomoo API endpoint.
- Boundary markers: The instructions do not define clear delimiters (e.g., XML tags or specific markers) to separate news content from instructions, nor do they instruct the agent to ignore commands within the data.
- Capability inventory: The skill utilizes
curlfor network operations and has the capability to display formatted external content to the user. - Sanitization: There is no mention of sanitizing or escaping the retrieved news titles or descriptions to prevent malicious instructions embedded in the news from influencing the agent's behavior.
Audit Metadata