yt-dlp downloads: video, audio, subtitles, transcripts, clips, playlists.
79%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/video-transcript-downloader/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow fetches captions/transcripts for a user-supplied video URL (YouTube via `youtube-transcript-plus`, otherwise yt-dlp subtitles), which are free text authored by outsiders, but the agent must select the specific URL rather than having outsiders push content into a monitored feed.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The setup command `npm ci` fetches and installs the `youtube-transcript-plus` tarball from the URL recorded in the lockfile, and the script imports it at runtime; the npm registry is only the transporter, and this third-party package has no established first-party provenance, though its lockfile integrity hash is enforced, so the tier is medium.
steipete/agent-scripts
2f82700
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.