orca-linear
Warn
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: MEDIUMPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill instructions explicitly tell the agent to "re-run it with escalated permissions" if the environment sandbox blocks execution (specifically when encountering a
runtime_access_deniederror). This encourages the agent to bypass security boundaries intended to restrict unauthorized access. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data from Linear, including ticket text, comments, and attachments. While the skill description includes a warning to treat this data as untrusted, the ingestion of attacker-controlled content from an external platform constitutes an indirect prompt injection attack surface.
- [COMMAND_EXECUTION]: The skill requires the agent to resolve and execute local CLI commands via the
ORCAexecutable. The instructions provide logic for selecting different binaries (e.g.,orca-dev,orca-ide,orca) based on the environment, which the agent then executes to perform tasks.
Audit Metadata