The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize information from external web sources. This functionality inherently involves processing untrusted data which could contain malicious instructions.
Ingestion points: The skill processes external data retrieved via the get_research_task_result tool as described in Step 5 of SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or boundary markers when the agent synthesizes findings.
Capability inventory: The skill utilizes run_research_task and get_research_task_result to interact with the Research API.
Sanitization: No explicit data sanitization or instruction-filtering steps are defined in the skill instructions.
[DATA_EXFILTRATION]: The skill documentation mentions the webhook_url parameter for the research task tool. This is a functional requirement for asynchronous completion notifications to external services like Slack or Zapier, provided by the user at runtime.

yutori-research