The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest external data from Go library documentation and local source files, which creates a potential vector for malicious instructions to influence the agent.
Ingestion points: The skill uses Read, Glob, and Grep tools to ingest local file content and the Context7 MCP tools to fetch external documentation and examples.
Boundary markers: There are no explicit delimiters or safety instructions provided to help the agent distinguish between data content and its own system instructions.
Capability inventory: The environment allows the use of the Bash tool for shell command execution, as well as file modification tools like Write and Edit.
Sanitization: The instructions do not define any validation or sanitization steps for the data fetched from documentation IDs or local source code.

golang-pro