linear-automation
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from an external source (Linear).
- Ingestion points: User-generated content is retrieved via tools like
LINEAR_GET_LINEAR_ISSUEandLINEAR_SEARCH_ISSUES. - Boundary markers: The skill does not provide instructions to use delimiters or ignore embedded instructions within the ingested data.
- Capability inventory: The agent has significant write permissions, including creating/updating issues, labels, and comments, and executing custom GraphQL mutations.
- Sanitization: No sanitization or validation of the ingested data is performed.
- [DYNAMIC_EXECUTION]: The tool
LINEAR_RUN_QUERY_OR_MUTATIONallows the agent to execute arbitrary GraphQL queries and mutations, enabling dynamic interaction with the Linear API that could be exploited if the agent is compromised by malicious input. - [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill instructions require the user to configure an external MCP server endpoint at
https://rube.app/mcpwhich provides the underlying tool functionality.
Audit Metadata