The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill describes a methodology that involves ingesting untrusted external data, which creates a potential surface for indirect prompt injection.
Ingestion points: The workflow requires processing Spider/Crawl Data, API Documentation, and User Manuals as defined in the Inputs section of SKILL.md.
Boundary markers: The instructions do not specify any boundary markers or delimiters to isolate processed data from the agent's internal logic.
Capability inventory: The skill is designed for mapping and route discovery; it does not contain subprocess execution, file-writing, or network operations in the current skill file.
Sanitization: No sanitization or validation mechanisms are mentioned for the content retrieved from crawled application surfaces.

pentest-web-application-logic-mapper