linear-pr
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Indirect Prompt Injection (HIGH): The skill is designed to process external content from Linear issues to automate development workflows.
- Ingestion points: Issue titles and descriptions are retrieved via
linear-cli contextand used inlinear-cli g prto generate PR metadata. - Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore instructions embedded within the Linear issue content.
- Capability inventory: The skill uses the
Bashtool to executegit,gh, andlinear-cli, providing a direct path from processed data to system commands and repository modification. - Sanitization: No sanitization or escaping of the issue content is mentioned, which could allow a malicious user to manipulate the agent's behavior via issue metadata.
- Command Execution (LOW): The skill relies on the Bash tool for all operations. While the documented commands are standard development tools, the use of a general-purpose shell provides a broad capability set that should be monitored, especially when handling dynamic input.
Recommendations
- AI detected serious security threats
Audit Metadata