linear
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curl,jq, and PowerShell'sInvoke-RestMethodto perform GraphQL queries and mutations against the Linear API atapi.linear.app. These operations are well-documented and restricted to the intended purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves and processes issue titles, descriptions, and comments from an external service (Linear).
- Ingestion points: External data enters the agent context through the outputs of the
curlcommands defined inSKILL.md(e.g., nodes returned byassignedIssuesandissueSearch). - Boundary markers: The skill does not specify clear delimiters or provide instructions for the agent to distinguish external API content from system prompts.
- Capability inventory: The skill allows the execution of shell commands (
curl,jq) and PowerShell commands. - Sanitization: There is no evidence of sanitization or filtering applied to the data retrieved from the Linear API before it is consumed by the agent.
Audit Metadata