linear-triage
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto send configuration data and a session API key to a vendor-provided automation backend (OPENHANDS_HOST). This behavior is consistent with the skill's stated purpose of setting up automation within the author's ecosystem. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from Linear issue titles and descriptions.
- Ingestion points: Linear issue titles, descriptions, and customer context are ingested for analysis as described in
SKILL.md. - Boundary markers: No boundary markers or delimitation instructions are present to prevent the agent from executing instructions potentially embedded within Linear issue content.
- Capability inventory: The skill possesses capabilities to list and modify issues via the Linear MCP and to register automation prompts via the
OPENHANDS_HOSTAPI. - Sanitization: There is no evidence of sanitization or filtering applied to the fetched issue data before it is processed by the agent.
Audit Metadata