The Agent Skills Directory

[PROMPT_INJECTION]: The skill functionality involves reading and analyzing a user's codebase, creating a surface for indirect prompt injection. 1. Ingestion points: The agent is instructed to read the project codebase to understand frameworks and authentication. 2. Boundary markers: There are no instructions to use delimiters or ignore instructions embedded in the user's code. 3. Capability inventory: The skill directs the agent to modify the codebase to add integration logic. 4. Sanitization: No explicit content validation or sanitization is mentioned for the processed files.
[EXTERNAL_DOWNLOADS]: Fetches implementation guidelines and code examples from official vendor-controlled domains. Evidence: The skill points to docs.credyt.ai/ai-integration.md and github.com/credyt/learn for detailed integration patterns.

billing-integration