SKILLEMALL.ai
GitHub ↗ RU Sign in

BD YouTube API

Use when YouTube data is needed through MyBrandMetrics: search YouTube videos, get video metadata, inspect channel info, browse playlists, list comments, check live broadcasts, query YouTube Analytics, and work with YouTube Reporting jobs. Covers YouTube Data API v3, YouTube Analytics API v2, and YouTube Reporting API v1 after YouTube is connected in MyBrandMetrics.

ClawHub Agent Skills author: clawbus v1.2.4 MIT-0 10 files body ≈ 1 537 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationYouTubeMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
89
Quality 40%
83
Run on models
none yet
Process rating
D
39/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 7

    ✓ No critical or high findings

    Medium and low: 7
    • medium Exfiltration net-credential-use SKILL.md:115
      Credential used in a network call (verify the destination is the intended service)
      curl -H "X-API-Key: $MYBRANDMETRICS_API_KEY" \
    • low Exfiltration net-credential-use references/catalog.json:62
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "curl": "curl -sS -X POST \"${MYBRANDMETRICS_API_BASE_URL:-https://api.mybrandmetrics.com}/discovery/youtube/abuseReports\" \\\n  -H \"X-API-Key: $MYBRANDMETRICS_API_KEY\" \\\n  -H \"Accept: applicati
      vendor-hostquoted
    • low Exfiltration net-credential-use references/catalog.json:152
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "curl": "curl -sS -X GET \"${MYBRANDMETRICS_API_BASE_URL:-https://api.mybrandmetrics.com}/discovery/youtube/activities\" \\\n  -H \"X-API-Key: $MYBRANDMETRICS_API_KEY\" \\\n  -H \"Accept: application/
      vendor-hostquoted
    • low Exfiltration net-credential-use references/catalog.json:199
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "curl": "curl -sS -X DELETE \"${MYBRANDMETRICS_API_BASE_URL:-https://api.mybrandmetrics.com}/discovery/youtube/captions\" \\\n  -H \"X-API-Key: $MYBRANDMETRICS_API_KEY\" \\\n  -H \"Accept: application
      vendor-hostquoted
    • low Exfiltration net-credential-use references/catalog.json:260
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "curl": "curl -sS -X GET \"${MYBRANDMETRICS_API_BASE_URL:-https://api.mybrandmetrics.com}/discovery/youtube/captions/${ID}\" \\\n  -H \"X-API-Key: $MYBRANDMETRICS_API_KEY\" \\\n  -H \"Accept: applicat
      vendor-hostquoted
    • low Exfiltration net-credential-use references/catalog.json:314
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
      "curl": "curl -sS -X POST \"${MYBRANDMETRICS_API_BASE_URL:-https://api.mybrandmetrics.com}/discovery/youtube/captions\" \\\n  -H \"X-API-Key: $MYBRANDMETRICS_API_KEY\" \\\n  -H \"Accept: application/j
      vendor-hostquoted
    • low Exfiltration net-credential-use references/curl.md:21
      Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
      curl -H "X-API-Key: $MYBRANDMETRICS_API_KEY" "${MYBRANDMETRICS_API_BASE_URL:-https://api.mybrandmetrics.com}/discovery/youtube/channels?part=…&mine=true"
      vendor-host

    Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)

    Process rating: all ten parameters 39/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 4 mutating operations with no state check
    • 40Consistency. Frontmatter name (YouTube API) differs from the folder (clawbus-youtube-unified-api)
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 100Steps. 15 steps
    • 100Execution cost. Instruction body is 1537 tokens

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 368: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 15 items
    • +4Has examples (7 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: suspicious
    This skill is not malware, but it exposes broad YouTube account-changing powers that are only partly disclosed and should be reviewed before installation.
    LLM: suspicious (high) · VirusTotal: · 28 May 2026