zenmux-feedback
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands and local bash scripts to check environment prerequisites, fetch repository labels, and manage documentation references. It specifically utilizes the
gh(GitHub CLI) for these operations. - [EXTERNAL_DOWNLOADS]: The
update-references.shscript performs agit cloneorgit pullfrom the vendor's official documentation repository (https://github.com/ZenMux/zenmux-doc.git) to ensure the agent uses current issue templates. - [DATA_EXFILTRATION]: The skill transmits user-generated feedback and bug reports to the external GitHub repository
ZenMux/zenmux-doc. This behavior is expected and aligns with the stated purpose of the skill. - [PROMPT_INJECTION]: The skill is designed to ingest and follow instructions from external YAML files found within the cloned repository's issue templates.
- Ingestion points: Files located at
skills/zenmux-feedback/references/zenmux-doc/.github/ISSUE_TEMPLATE/*.yml. - Boundary markers: None; the skill explicitly treats these remote files as the "source of truth" for its operation.
- Capability inventory: The agent has the ability to execute shell commands and interact with the GitHub API via the
ghtool. - Sanitization: There is no verification or sanitization of the remote template content before the agent adopts its instructions.
Audit Metadata