azure-devops
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the Membrane CLI tool (
@membranehq/cli) from the npm registry. This is a vendor-owned utility used for managing authentication and executing Azure DevOps actions. - [COMMAND_EXECUTION]: The instructions utilize shell commands (
membrane,npx) to interact with the Membrane platform, discover actions, and perform API requests against Azure DevOps. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from Azure DevOps (such as work items, repository content, and pipeline logs) which could contain hidden instructions for the agent.
- Ingestion points: Data retrieved through
membrane action run,membrane action list, andmembrane requestfrom Azure DevOps APIs. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the retrieved data.
- Capability inventory: The agent can perform read and write operations on Azure DevOps records and repositories via the CLI.
- Sanitization: No explicit sanitization, validation, or filtering of content retrieved from the external API is specified in the skill body.
Audit Metadata