youtube-full
Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-02-01.
The youtube-full skill is a straightforward API wrapper for TranscriptAPI.com services with MODERATE security concerns. The skill provides legitimate YouTube data access functionality (transcripts, search, channels, playlists) through a third-party API service. Primary security concern is the recommended credential storage method which could expose API keys through shell configuration files. The skill contains no executable scripts (only curl examples in documentation), no data exfiltration patterns, no prompt injection attempts, and no malicious code. The functionality matches the description accurately. The main risk is credential exposure through insecure storage practices recommended in the setup instructions. Missing optional metadata reduces transparency but does not constitute a security threat.
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
Complete YouTube toolkit — transcripts, search, channels, playlists, and metadata all in one skill. Use when you need comprehensive YouTube access, want to search and then get transcripts, browse channel content, work with playlists, or need the full suite of YouTube data endpoints. The all-in-one YouTube skill for agents.
- Package
- 1 file, 5.8 KB
- SKILL.md
- 605 words, 12+ sections
- Code
- None. Instructions only.
- Requires
- env:
TRANSCRIPT_API_KEY - Homepage
- https://transcriptapi.com
SKILL.md covers: YouTube Full · Setup · Transcript — 1 credit · Search — 1 credit · Videos · Channels · Channels · Resolve handle — FREE · Latest 15 videos — FREE · All channel videos — 1 credit/page · First page (100 videos) · Next pages
Findings
MEDIUM Hardcoded API Key Storage in Shell Configuration Data Exfiltrationllm
The skill instructs users to store the API key directly in shell configuration files (~/.zshenv) using echo commands. This creates a persistent credential that could be exposed through shell history, backup files, or if the configuration file is inadvertently shared. While the API key is required for functionality, the storage method lacks security best practices such as file permission warnings or encrypted credential storage recommendations.
SKILL.md:12
Store: `echo 'export TRANSCRIPT_API_KEY="sk_..."' >> ~/.zshenv && source ~/.zshenv`What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 5.8 KB |
External hosts referenced
transcriptapi.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-full
- Raw scan result: youtube-full-scan.json
- Badge for your README:
- Request a re-scan