Audit History

One confirmed issue instructs unattended execution of an npx skill-update command without user approval. The remaining static matches are false positives caused by Markdown backticks, static CSS/reference content, local test code, and the bundled minified GSAP library.

The static score is dominated by false matches on Markdown backticks, CSS borders, valid WOFF2 fonts, and the minified GSAP distribution. One high-confidence semantic risk remains: the skill orders an unpinned npx package update to run silently without user consent.

Most static hits are false positives from Markdown inline code, CSS border declarations, and a bundled minified GSAP library. The real security concern is operational: the skill asks the agent to run local CLI tools, including npx HyperFrames and ffmpeg/ffprobe, against user media. No prompt injection attempt or credential exfiltration instructions were found in the reviewed files.

Most static findings are false positives caused by Markdown formatting, CSS design references, WOFF2 font assets, and a minified GSAP vendor bundle. No prompt injection, credential exfiltration, or malicious payload intent was found. One medium semantic risk remains because the workflow executes unpinned npx hyperframes commands.

Manual adjudication found the static findings to be false positives caused by markdown examples, static HTML references, bundled fonts, and a minified GSAP browser library. No prompt injection, credential access, data exfiltration, or malicious command behavior was found in the reviewed context.