azure-devops
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
curlandgitto manage repositories and call Azure DevOps REST APIs. - [CREDENTIALS_UNSAFE]: The documentation suggests embedding the
AZURE_DEVOPS_TOKENdirectly into the git remote URL viagit remote set-url, which results in the sensitive token being stored in plain text within the workspace's.git/configfile. - [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface as it is designed to ingest and process data from external Azure DevOps sources such as pull request descriptions and repository files.
- Ingestion points: Data retrieved from Azure DevOps API endpoints (e.g.,
_apis/git/pullrequests) and git repository content. - Boundary markers: No delimiters or instructions to ignore embedded commands are specified.
- Capability inventory: The skill utilizes
bash,git, andcurl, providing file system, network, and command execution capabilities. - Sanitization: No sanitization or validation logic is defined for the external data being processed.
Audit Metadata