The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions.
[COMMAND_EXECUTION]: The skill utilizes the agent-native command-line tool to publish generated visual artifacts. This is a legitimate vendor resource used for the skill's primary function.
[PROMPT_INJECTION]: The skill analyzes external data from repositories and GitHub. This indirect prompt injection surface is mitigated by clear negative constraints instructing the agent to never publish secrets, credentials, or unauthorized private source excerpts discovered during the inspection process.

visual-answer