linear

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the user to install the '@membranehq/cli' package from NPM. This is a trusted vendor resource provided by 'membrane' (membranedev) to facilitate the integration.\n- [COMMAND_EXECUTION]: The skill utilizes the 'membrane' command-line interface to perform actions such as creating issues, managing projects, and running API requests. These commands are used as intended for the skill's primary functionality.\n- [PROMPT_INJECTION]: The skill ingests data from external Linear sources, such as issue comments and descriptions, creating a surface for potential indirect prompt injection. This is a standard requirement for the intended ticketing use-case.\n
  • Ingestion points: 'list-comments', 'list-issues', and 'search-issues' actions (SKILL.md)\n
  • Boundary markers: None specified in the instructions\n
  • Capability inventory: 'membrane action run' and 'membrane request' for API interaction (SKILL.md)\n
  • Sanitization: Not explicitly mentioned in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 11:12 AM