The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill includes shell command templates that use curl to fetch repository metadata and file contents from GitHub (api.github.com and raw.githubusercontent.com). These references target a well-known service for the purpose of static inspection and metadata retrieval.
[DATA_EXFILTRATION]: No data exfiltration patterns were detected. The skill's primary function is to define a protocol for detecting data exfiltration and credential theft in other skills.
[PROMPT_INJECTION]: The instructions are clear, meta-instructional guidelines for a security task and do not attempt to override the host agent's safety protocols or core instructions.
[COMMAND_EXECUTION]: The skill provides utility commands for the agent to use curl and jq for auditing. These are limited to read-only operations against trusted GitHub APIs.
[SAFE]: The skill is a security tool designed to mitigate risks by providing a structured vetting protocol. It does not contain executable scripts, hidden code, or dangerous dependencies.

skill-vetter