orca-linear

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes the vendor's orca CLI tool (or variants orca-dev/orca-ide) to perform project management tasks.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of content from Linear tickets, which may contain untrusted data.
  • Ingestion points: External data enters the agent context via orca linear command outputs.
  • Boundary markers: The instructions contain an explicit directive for the agent to treat ticket text as untrusted and ignore any instructions found within it.
  • Capability inventory: The agent has the ability to execute shell commands through the orca binary and read environment variables.
  • Sanitization: The skill relies on the agent's adherence to the provided security guidance regarding untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:25 AM
Security Audit — agent-trust-hub — orca-linear