subtitles

SAFE max severity MEDIUMSkillSpector Safe 0 registry clawhub.ai last scanned 2026-02-01 1 scan

Verdict safe, but 2 findings (2 medium), mainly data exfiltration. Most recent scan 2026-02-01.

The 'subtitles' skill is a straightforward YouTube subtitle fetching tool that uses a legitimate third-party API (TranscriptAPI.com). The skill has MEDIUM severity concerns around credential management and data privacy, but no critical security threats. The primary issues are: (1) inadequate guidance on secure API key storage, (2) lack of privacy disclosure about sending video URLs to a third party, (3) missing optional metadata fields, and (4) limited error handling for network failures. The skill does not contain malicious code, prompt injection attempts, data exfiltration, or command injection vulnerabilities. It is a legitimate utility skill that would benefit from enhanced security guidance and privacy disclosures.
Scanner's overall assessment (LLM analyzer)

Findings2

Critical0

High0

Medium2

Low0

Analyzersstatic behavioral llm trigger meta

Second scanner: NVIDIA SkillSpector

VerdictSafe 0

Score0 / 100

Issues0

Version2.12.0 (static)

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

Get subtitles from YouTube videos for translation, language learning, or reading along. Use when the user asks for subtitles, subs, foreign language text, or wants to read video content. Supports multiple languages and timestamped output for sync'd reading.

Package: 1 file, 2.7 KB
SKILL.md: 266 words, 5 sections
Code: None. Instructions only.
Requires: env: TRANSCRIPT_API_KEY
Homepage: https://transcriptapi.com

SKILL.md covers: Subtitles · Setup · GET /api/v2/youtube/transcript · Tips · Errors

Findings

MEDIUM Hardcoded API Key Requirement Without Validation Data Exfiltrationllm

The skill requires users to store a TRANSCRIPT_API_KEY in their shell environment (~/.zshenv) but provides no validation, security guidance, or warnings about key exposure. The instructions encourage direct shell export without discussing secure credential management practices. While the API service itself appears legitimate, the skill does not validate the key format, warn about accidental commits to version control, or suggest more secure storage methods.

SKILL.md

Store: `echo 'export TRANSCRIPT_API_KEY="sk_..."' >> ~/.zshenv && source ~/.zshenv`

Remediation: Add security guidance: (1) Warn users about keeping API keys out of version control, (2) Suggest using a secrets manager or encrypted credential store, (3) Validate API key format before making requests, (4) Document key rotation procedures, (5) Consider using environment-specific configuration files with restricted permissions instead of shell rc files.

MEDIUM Potential Data Exposure via Third-Party API Data Exfiltrationllm

The skill sends YouTube video URLs to an external third-party API (transcriptapi.com) which could create a privacy concern. Users' viewing history and video interests are transmitted to this external service. While the service appears legitimate, there is no disclosure about data retention, logging, or privacy policies. The skill metadata indicates API key requirement but does not inform users that their video access patterns will be shared with a third party.

SKILL.md

Fetch YouTube video subtitles via [TranscriptAPI.com](https://transcriptapi.com)... curl -s "https://transcriptapi.com/api/v2/youtube/transcript?video_url=VIDEO_URL"

Remediation: Add privacy disclosure: (1) Clearly state that video URLs are sent to a third-party service, (2) Link to TranscriptAPI.com's privacy policy, (3) Warn users about potential data retention/logging, (4) Consider adding a confirmation prompt before first use, (5) Document what data is transmitted (video URLs, API keys) and what is received.

What is in the package

File	Kind	Size
`SKILL.md`	doc	2.7 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/subtitles
Raw scan result: subtitles-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/clawhub-ai-subtitles.svg)
Request a re-scan