social-to-imgur

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill fetches the Imgur Client ID from the macOS keychain and then requires that value be placed verbatim into a curl Authorization header for upload, which forces the agent to handle and emit the secret directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text at runtime via user-provided social media/post URLs, which are passed into yt-dlp --get-thumbnail and then into curl for thumbnail download (text/content derived from the fetched page), before uploading to Imgur.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly instructs the agent/user to add and update credentials in the macOS keychain (and creates temp files), which modifies system state and manages sensitive secrets and therefore can compromise the machine.