The Agent Skills Directory

Indirect Prompt Injection (LOW): The skill processes content from definition.md and design.md to generate structured descriptions and titles for Linear issues. This ingestion of untrusted data could be exploited if those files contain malicious instructions designed to manipulate the agent's behavior during the synchronization process.
Ingestion points: definition.md and design.md located in docs/issues/YYYY-MM-DD-<slug>/.
Boundary markers: Absent. The skill does not define clear delimiters or include 'ignore embedded instructions' warnings when reading the source artifacts.
Capability inventory: The agent can list teams, create/update issues, and create/update documents via the linear-server toolset.
Sanitization: Absent. The instructions focus on formatting and summarizing the content but do not mandate sanitization or escaping of the input data to prevent injection attacks.

syncing-linear