linear-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands via the
orcabinary. It uses logic to select the correct executable based on environment variables (ORCA_CLI_COMMAND,ORCA_DEV_REPO_ROOT) to prevent conflicts with native system tools such as the GNOME screen reader on Linux systems.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from Linear issues, establishing an injection surface.\n - Ingestion points: Data enters the context through output from the
orca linear issuecommand mentioned inSKILL.md.\n - Boundary markers: The instructions explicitly command the agent to treat returned fields as untrusted source data and specifically not to follow instructions contained within the ticket text.\n
- Capability inventory: The skill allows the agent to execute shell commands and modify remote ticket states.\n
- Sanitization: The skill relies on the agent's adherence to the safety instructions provided in the skill body rather than automated content sanitization.
Audit Metadata