DJ set ripper
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill’s download workflow is coherent, but its helper can rename or move files using unsanitized track names extracted from web pages, so it needs review before use.
Before installing, review the external dj-mp3-sourcer workflow and required media tools. Use this only in a dedicated download folder, inspect the extracted tracklist before downloads, and do not run the normalization step until artist/title fields are sanitized to safe filenames.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A crafted or bad tracklist could cause downloaded MP3s to be renamed into unexpected locations or make the cleanup/organization step affect paths the user did not intend.
Artist and title values from the tracklist JSON are used directly as path components for mv. If those values contain slashes, '..', or other unsafe filename content, a malformed or malicious tracklist could move files outside the intended download folder.
TARGET="${ARTIST} - ${TITLE}.mp3" ... mv "$MATCH" "$DIR/$TARGET"Sanitize artist and title values before use as filenames, reject path separators and traversal strings, resolve the final path to ensure it remains inside the output directory, and consider a dry-run/confirmation before renaming.
A malicious page could influence what tracks the agent thinks it found, which could lead to wrong downloads or unsafe filenames if not validated.
The skill intentionally feeds untrusted web page content into the model for tracklist extraction. That is purpose-aligned, but page descriptions or comments could contain prompt-injection text that skews extraction or filename data.
Fetch the set URL and extract raw text (description, metadata, comments) ... Feed the raw page content to the model ... Raw content: """ {description_text} """Treat fetched page text strictly as data, add explicit prompt-injection resistance in the extraction prompt, and review the parsed tracklist before downloading or renaming files.
Users may run unreviewed external tooling or another skill that was not included in this artifact review.
The skill relies on another skill and several external binaries, while the registry declares no required binaries and no install spec. This is disclosed in the README, but not fully captured in metadata.
Same as [dj-mp3-sourcer](https://clawhub.ai/Robinnnnn/dj-mp3-sourcer) (yt-dlp, ffmpeg/ffprobe, spotdl). No additional dependencies.
Review and install dj-mp3-sourcer, yt-dlp, ffmpeg/ffprobe, spotdl, and jq from trusted sources before use, and update the skill metadata to declare required tools.
Parallel sessions may make it harder to monitor exactly which downloads are running and can compound mistakes from a bad parsed tracklist.
The workflow delegates batches of track downloads to spawned sessions/sub-agents. This is bounded and purpose-aligned, but it does create parallel agent activity that shares track/task context and writes into the same output area.
Use `sessions_spawn` to parallelize downloads (batch of 3-5 at a time to avoid rate limits)
Keep batch sizes small, wait for all sessions to finish before normalization as documented, and review the parsed tracklist before spawning download batches.