ui-update
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches update assets by cloning a remote repository from GitHub. It specifically uses a pinned commit hash to ensure the integrity of the downloaded content and mandates user authorization before performing the clone operation.
- [COMMAND_EXECUTION]: Uses standard shell commands for project discovery and repository management, such as
find,cat, andgit. The execution is transparently described and limited to the stated purpose of updating project files. - [DATA_EXFILTRATION]: No unauthorized data transmission was detected. Network activity is limited to downloading updates from a vendor-associated repository, and no sensitive local information is included in these requests.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files during the update process. It mitigates potential risks by instructing the agent to perform a manual inspection of the candidate files and to explicitly reject executable scripts or unexpected binaries before they are applied to the project.
Audit Metadata