youtube-data
Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-02-01.
The youtube-data skill is a documentation-only skill that provides instructions for accessing YouTube data via TranscriptAPI.com using curl commands. It contains NO executable scripts (Python/Bash files), making it inherently lower risk than skills with code execution capabilities. The primary security concerns are MEDIUM severity issues around credential management practices demonstrated in the documentation, and LOW severity issues related to missing optional metadata and incomplete documentation. The skill does not exhibit prompt injection, data exfiltration code, command injection, or other critical threats. The external API calls are explicitly documented and expected behavior for a YouTube data access skill. No tool restriction violations exist since no allowed-tools are declared and no scripts are present.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Access YouTube video data — transcripts, metadata, channel info, search, and playlists. A lightweight alternative to Google's YouTube Data API with no quota limits. Use when the user needs structured data from YouTube videos, channels, or playlists without dealing with Google API setup, OAuth, or daily quotas.
- Package
- 1 file, 4.1 KB
- SKILL.md
- 397 words, 8 sections
- Code
- None. Instructions only.
- Requires
- env:
TRANSCRIPT_API_KEY - Homepage
- https://transcriptapi.com
SKILL.md covers: YouTube Data · Setup · Video Data (transcript + metadata) — 1 credit · Search Data — 1 credit · Channel Data · Playlist Data — 1 credit/page · Credit Costs · Errors
Findings
MEDIUM Hardcoded API Key Exposure Risk in Documentation Data Exfiltrationllm
The skill instructions demonstrate storing the API key in ~/.zshenv using a plain echo command, which could lead to accidental exposure through shell history, logs, or insecure file permissions. While this is a documentation example rather than hardcoded credentials in code, it teaches insecure credential management practices to users.
SKILL.md
Store: `echo 'export TRANSCRIPT_API_KEY="sk_..."' >> ~/.zshenv && source ~/.zshenv`What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 4.1 KB |
External hosts referenced
transcriptapi.com i.ytimg.com www.youtube.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
TRANSCRIPT_API_KEY
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/youtube-data
- Raw scan result: youtube-data-scan.json
- Badge for your README:
- Request a re-scan