The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external documents, which inherently creates a surface for indirect prompt injection. Ingestion points: The instructions require the agent to analyze user-provided contracts, KYC records, and legal notices (SKILL.md). Boundary markers: The instructions do not specify the use of delimiters to separate user data from the agent's core instructions. Capability inventory: The skill's functionality is limited to generating text-based work products like memos and checklists, and it does not utilize high-risk tools for network access or system modification. Sanitization: No specific filtering or escaping mechanisms for the analyzed content are defined.

aml-verdachtsmeldung-fiu-leitfaden