upgrade
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform directory operations (mkdir, rm -rf), file synchronization (rsync), and to execute the local binary notfair-update-check to check for updates. It also runs a Python script to update the local installed_plugins.json configuration file.
- [EXTERNAL_DOWNLOADS]: Fetches the latest plugin code from the vendor's remote git repository using git fetch and git reset. This is a primary function of the upgrade skill and targets the vendor's own infrastructure.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by reading and summarizing CHANGELOG.md in Step 8. Evidence: 1. Ingestion point: CHANGELOG.md. 2. Boundary markers: Absent. 3. Capability inventory: Bash, Read, and AskUserQuestion. 4. Sanitization: Absent beyond summarization instructions. While this allows external data to enter the prompt context, the source is the vendor's own repository and the behavior is limited to summarization.
Audit Metadata