The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process information from an external documentation site (docs.bullmq.io). This creates a surface for indirect prompt injection, where malicious instructions hidden in the processed documentation could influence the agent's behavior.
Ingestion points: External content from docs.bullmq.io as specified in the workflow in SKILL.md and the selective index in references/topic-map.md.
Boundary markers: The skill requires grounding answers in live documentation and providing specific citations for every claim, which helps distinguish between documentation content and agent instructions.
Capability inventory: The skill's primary function is informational retrieval and answering questions; it does not request file system access, shell execution, or sensitive data access.
Sanitization: The instructions do not specify any sanitization or validation of the fetched external content.

bullmq-docs