The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs the agent to retrieve and act upon untrusted data from an external source (Linear issues).
Ingestion points: The agent uses mcp__linear-server__get_issue and mcp__linear-server__extract_images to ingest issue descriptions and visual context.
Boundary markers: There are no instructions to treat external data as untrusted or to ignore embedded commands within issue descriptions.
Capability inventory: The skill allows the agent to create/update issues, post comments, and perform implementation tasks based on the ingested content.
Sanitization: No sanitization or validation of the retrieved text or image data is described.

linear