vss-search
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [SAFE]: The skill instructions and documentation align with the stated purpose of providing a video search interface. No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were found.
- [COMMAND_EXECUTION]: The skill utilizes
curlandjqto interact with a video management service. These commands are used for legitimate API requests such as checking health status, uploading video files, and querying the search index. The use of a temporary file (/tmp/idmap.json) for data processing withjqfollows standard scripting practices. - [DATA_EXFILTRATION]: Data movement is restricted to the user-defined service host. While the skill facilitates the upload of video files and transmission of search queries, these actions are essential to the primary function of the skill and do not involve unauthorized exfiltration of sensitive information to third-party domains.
Audit Metadata