The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied 'Positioning & Messaging documentation' which represents an attack surface for instructions embedded in external data. * Ingestion points: The skill explicitly requests and analyzes user-provided documentation in SKILL.md. * Boundary markers: The instructions do not define boundary markers or delimiters to separate untrusted user data from the system prompt. * Capability inventory: The skill is limited to generating markdown text and lacks access to network tools, file system writes, or command execution capabilities. * Sanitization: There is no evidence of input sanitization or validation of the provided documentation content.

customer-segments