youtube-tools
Fetch transcripts and create structured watching guides / summaries for YouTube videos. Use when the user asks to (1) get, fetch, extract, or download a transcript or captions from a YouTube video URL, or (2) summarize, create a watching guide, or produce a structured summary of a YouTube video. Trigger on youtube.com/watch, youtu.be, or youtube.com/shorts links.
79
—
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The 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.
Why it was flagged
Third-party content exposure detected (high risk: 0.95). The required runtime path fetches YouTube transcripts/auto-subs from a user-supplied `<youtube-url>` (public web content) via `defuddle parse ... --markdown` or `yt-dlp --write-auto-subs`, and that readable transcript Markdown/VTT text is then ingested into the agent’s LLM for analysis and guide generation.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
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.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.70). The skill's recommended runtime command "npx defuddle parse <youtube-url> --markdown" causes npm to fetch and execute the remote "defuddle" package from the npm registry (e.g. https://registry.npmjs.org/defuddle) at runtime, which executes remote code and is required by the workflow.
- Repository
- ceshine/ceshine-agent-skills
- Commit
b0c328d
- Audited
- Security analysis
Is this your skill?
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.