The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several shell commands to manage the publishing workflow, including gh gist create for gist management, git for uploading image assets, and curl for verifying the accessibility of the published images.
[DATA_EXFILTRATION]: The skill's primary function is to transmit local data (markdown reports and PNG screenshots) to external GitHub Gist storage. While this is data movement, it is the explicit and documented purpose of the skill. The instructions emphasize the use of 'secret' gists to protect potentially sensitive internal information contained within the reports.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes test reports and screenshot files. If these reports contain content generated from untrusted external sources, they could theoretically harbor malicious instructions. However, the skill acts primarily as a transport mechanism, and the instructions focus on path manipulation rather than interpreting the content as agent commands.

publish-gist-report