cloud-native-readiness
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell utilities such as
grep,find, andwcto analyze the local or cloned filesystem of a project. These commands are executed to identify frameworks, dependencies, and code patterns relevant to containerization readiness. - [EXTERNAL_DOWNLOADS]: The skill includes functionality to clone external repositories from GitHub for analysis. This is an intended feature of the assessment workflow and targets user-provided URLs.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and reasons about the contents of untrusted external repositories.
- Ingestion points: Source code files, configuration files, and directory names in the project being assessed (identified in
modules/assess.mdandmodules/detect.md). - Boundary markers: The skill currently lacks explicit delimiters or instructions to the agent to disregard instructions found within the code being analyzed.
- Capability inventory: The skill uses shell command execution, network access for cloning repositories, and the ability to invoke the
dockerfile-skilltool. - Sanitization: There is no evidence of content sanitization or instruction-filtering for the data retrieved from the analyzed repositories.
Audit Metadata