SKILLEMALL.ai
GitHub ↗ RU Sign in

CC youtube-comment-moderator

AI-powered YouTube comment moderation. Fetches comments, classifies them (spam, question, praise, hate, neutral, constructive), drafts replies, and deletes spam. Works with any YouTube channel via OAuth. Use when moderating YouTube comments, setting up auto-replies, analyzing comment sentiment, managing spam, or building a comment moderation pipeline.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Dhruv Kar v1.0.1 MIT-0 15 files · 5 scripts body ≈ 1 622 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

AI-powered YouTube comment moderation.

As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureYouTubeGoogle CloudMedia 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
C
81/100
safety, quality, tests
Safety 60%
77
Quality 40%
88
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Broad scope
If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
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 · 6

  • high Broad scope meta-requests-env-secret SKILL.md:1
    Skill asks the runtime to inject credential env vars into its sandbox: YOUTUBE_API_KEY, GEMINI_API_KEY, YT_MOD_CLIENT_SECRET (high-value: GEMINI_API_KEY) — verify each one is needed for the stated purpose
    required_environment_variables: YOUTUBE_API_KEY, GEMINI_API_KEY, YT_MOD_CLIENT_SECRET
Medium and low: 5
  • low Exfiltration read-dotenv SKILL.md:38
    Reads a .env file
    source .env
  • low Exfiltration read-dotenv SKILL.md:65
    Reads a .env file
    source .env && python3 scripts/setup.py --auth-url
  • low Exfiltration read-dotenv SKILL.md:76
    Reads a .env file
    source .env && python3 scripts/setup.py --exchange-code "http://127.0.0.1:8976/callback?code=<CODE>"
  • low Exfiltration read-dotenv SKILL.md:101
    Reads a .env file
    source .env && python3 scripts/moderate.py --all-videos --dry-run
  • low Exfiltration read-dotenv SKILL.md:110
    Reads a .env file
    source .env && python3 scripts/moderate.py --all-videos

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "env"

Process rating: all ten parameters 50/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 14 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 65Failures and branches. 3 branches
  • 85Steps. 21 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1622 tokens
  • 100Progress reporting. Reports progress

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
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 353: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 21 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)
  • +3All 5 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

External checks

ClawHub: suspicious
The skill is a coherent YouTube moderation tool, but its auto mode can delete comments and post replies from LLM output with weak safeguards around OAuth and stored tokens.
LLM: suspicious (high) · VirusTotal: · 11 Sept 2026