jetbrains-youtrack
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from npm. This is a vendor-provided tool required for the skill's functionality and is used to manage connections and authenticate with the Membrane platform. - [COMMAND_EXECUTION]: The skill documentation includes several commands for the
membraneCLI, such asmembrane login,membrane connection ensure, andmembrane action run. These commands are used to establish a secure link between the agent and the JetBrains YouTrack API via the vendor's proxy service. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from JetBrains YouTrack, including issue descriptions and comments. This presents a surface where untrusted data could enter the agent's context.
- Ingestion points: Data enters via YouTrack API responses when fetching issues or comments through
membrane action runormembrane request. - Boundary markers: The instructions do not explicitly define delimiters for external data.
- Capability inventory: The skill has the capability to perform network requests and run API actions via the Membrane CLI.
- Sanitization: No specific sanitization or filtering of the external issue/comment content is described within the skill instructions.
Audit Metadata