The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external tickets and issues in Linear Multiworkspace, which constitutes an attack surface for indirect prompt injection where malicious instructions could be embedded in ticket content.
Ingestion points: Data enters the agent context through the apideck.issueTracking.tickets.list method and the Apideck Proxy API as described in SKILL.md.
Boundary markers: No specific boundary markers or "ignore instructions" warnings are defined in the skill instructions to delimit external ticket data.
Capability inventory: The skill allows the agent to perform network operations via curl and the @apideck/unify SDK to interact with the Apideck platform (unify.apideck.com).
Sanitization: The instructions do not specify any sanitization or filtering logic for the ingested ticket data before it is processed by the agent.

linear-multiworkspace