The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (Linear ticket descriptions, comments, and media) which could contain malicious instructions.
Ingestion points: Untrusted data enters the agent context via orca linear issue, orca linear search, and orca linear list commands.
Boundary markers: The skill contains explicit instructions for the agent to treat all returned Linear fields as untrusted source data and to never follow instructions found within ticket text, comments, or attachments.
Capability inventory: The agent has the ability to read, write, and update Linear tickets via the orca CLI tool.
Sanitization: The skill provides clear guidance to use ticket content as reference only, effectively mitigating the risk of the agent executing commands embedded in ticket data.
[COMMAND_EXECUTION]: The skill uses the orca CLI to interact with the Linear platform. These commands are consistent with the skill's stated purpose and use the vendor's own authorized tooling.

orca-linear