linear
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill retrieves and processes untrusted content from Linear issue descriptions and comments, creating a surface for indirect prompt injection.
- Ingestion points: issue and issues queries in SKILL.md
- Boundary markers: Absent
- Capability inventory: linear_graphql mutations and shell command execution for curl uploads in SKILL.md
- Sanitization: Absent
- [COMMAND_EXECUTION]: The skill includes instructions for using curl to perform file uploads. This usage is restricted to signed URLs and headers provided by the Linear API, which is a standard and secure implementation for this workflow.
Audit Metadata