The Agent Skills Directory

[DATA_EXFILTRATION]: The skill transmits user-provided Go source code and git diffs to the vendor's API at gopherguides.com to perform audits and reviews. This is a core part of the skill's functionality as a Go training tool.
[COMMAND_EXECUTION]: The skill executes shell commands using curl and a local cache script (cache-api.sh) to interact with the Gopher Guides API and manage local data stored in .claude/gopher-guides-cache.json.
[PROMPT_INJECTION]: The skill processes untrusted user data (code and diffs), which presents an indirect prompt injection surface.
Ingestion points: The audit and review endpoints (in SKILL.md) ingest user code and diff output directly into JSON payloads for the API.
Boundary markers: No specific boundary markers or 'ignore' instructions are used when embedding user content into the API requests.
Capability inventory: The skill possesses the ability to execute shell commands (curl) and perform network requests to the vendor domain.
Sanitization: There is no evidence of sanitization or escaping of the user-provided code before it is passed to the API or the local script.

gopher-guides