xyq-nest-skill
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses Python's
urllibto make HTTP requests to the platform's API. While the instructions suggest executing scripts viapython3 {baseDir}/scripts/..., these are part of the skill's own distribution and perform legitimate integration tasks. - [EXTERNAL_DOWNLOADS]: The
download_results.pyscript downloads generated media files from URLs provided by the API. It usesurllib.request.urlopenwith a standardUser-Agent. These downloads are triggered by the user's generation requests. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided messages and external API responses (status updates). It explicitly instructs the agent to act as a "transporter" and avoid modifying or interpreting the prompts locally, which reduces the risk of the agent being manipulated by malicious instructions embedded in data, though a surface for indirect injection exists when the agent displays API results to the user.
Audit Metadata