mass-deploy-ux
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle and display external data such as device logs and status messages, which could be used to inject instructions.
- Ingestion points: Data is processed via the
DeviceListModelandclassify_errorfunctions inSKILL.md. - Boundary markers: No specific delimiters or warnings to ignore instructions within the logs are present in the provided snippets.
- Capability inventory: The skill is granted
WriteandEditpermissions in theSKILL.mdfrontmatter. - Sanitization: The implementation hints do not include logic for sanitizing or escaping external log content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The
README.mdfile links to an external repository for additional tooling athttps://github.com/NerdBase-by-Stark/skill-forge, which is a vendor-owned resource. - [COMMAND_EXECUTION]: The
README.mdinstructs the user to run./install.sh mass-deploy-uxfor installation. This references a local script that was not included in the analyzed files, making its contents unverifiable.
Audit Metadata