The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by reading and processing external codebase data while possessing significant file-system and command-execution capabilities.
Ingestion points: Instruction 1 in SKILL.md directs the agent to audit existing endpoint definitions and contracts using Grep and Read tools.
Boundary markers: The skill does not provide specific delimiters or instructions to ignore embedded prompts found within the source code or comments.
Capability inventory: The agent has access to Write, Edit, and Bash (restricted to api:version-* patterns), enabling potential code modifications based on the content of audited files.
Sanitization: No validation or escaping of the ingested code content is described in the instructions.
[SAFE]: References to external domains tonsofskills.com, intentsolutions.io, and jeremylongshore.com are vendor-controlled resources and are documented neutrally.

versioning-apis