SKILLEMALL.ai
RU Sign in

FD permission-vending-machine

Multi-channel approval system for AI agent permissions. GATES sensitive operations (file deletion, git force-push) behind human approval. Notifies via iMessage, Email, Discord, Telegram, Slack — and enforces time-limited grants before dangerous commands run. Use when an agent needs permission to delete files, force-push, or perform destructive operations.

Not recommendedcritical or high security findings · low grade F
ClawHub Agent Skills author: Tyler v1.1.1 MIT-0 33 files body ≈ 827 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureSlackDiscordTelegramAI and agentsInfrastructuretype 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
F
35/100
safety, quality, tests
Safety 60%
0
Quality 40%
88
Run on models
none yet
Process rating
D
43/100
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

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

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 16

  • high Dangerous commands cmd-persistence docs/PLATFORMS.md:34
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/ai.flume.pvm.plist
  • high Dangerous commands cmd-persistence docs/PLATFORMS.md:176
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    Register-ScheduledTask -Action $action -Trigger $trigger -TaskName "PVM" -RunLevel Highest
  • high Dangerous commands cmd-persistence README.md:113
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/ai.flume.pvm.plist
  • high Dangerous commands cmd-persistence README.md:251
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/ai.flume.pvm.plist   # start
  • high Dangerous commands cmd-persistence README.md:252
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/ai.flume.pvm.plist # stop
  • high Dangerous commands cmd-persistence SKILL.md:32
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/ai.flume.pvm.plist
Medium and low: 10
  • medium Dangerous commands cmd-persistence README.md:248
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    The plist is at `~/Library/LaunchAgents/ai.flume.pvm.plist`:
    quoted
  • medium Dangerous commands cmd-persistence src/pvm/setup_wizard.py:369
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    print(f"\n  Start:   launchctl load ~/Library/LaunchAgents/ai.flume.pvm.plist")
    code literal
  • medium Dangerous commands cmd-persistence src/pvm/setup_wizard.py:420
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    print(f"   To start: launchctl load {plist_path}")
    code literal
  • low Dangerous commands cmd-background-process docs/PLATFORMS.md:105
    Starts a background / autostarted process
    sudo systemctl enable pvm
  • low Exfiltration exfil-webhook-url README.md:105
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    webhook_url: "https://discord.com/api/webhooks/..."
    placeholder
  • low Exfiltration exfil-webhook-url SKILL.md:79
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    webhook_url: "https://discord.com/api/webhooks/..."
    placeholder
  • low Exfiltration exfil-webhook-url src/pvm/setup_wizard.py:180
    Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition; the skill's own vendor host)
    "Must be a Discord webhook URL" if not v.startswith("https://discord.com/api/webhooks/") else q.ValidationResult.SUCCESS,
    detectorvendor-host
  • low Exfiltration exfil-webhook-url src/pvm/setup_wizard.py:292
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    default=existing.get("channels", {}, {}).get("slack", {}).get("webhook_url", "https://hooks.slack.com/..."),
    placeholder
  • low Dangerous commands cmd-privilege src/pvm/setup_wizard.py:447
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    print(f"   sudo mv {unit_path} /etc/systemd/system/pvm.service")
    code literal
  • low Dangerous commands cmd-background-process src/pvm/setup_wizard.py:449
    Starts a background / autostarted process (string literal in code, not executed)
    print("   sudo systemctl enable pvm")
    code literal

Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 43/100

  • 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
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 100Steps. 11 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 827 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 357: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 11 items
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)

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

External checks

ClawHub: suspicious
This appears to be a real permission-approval tool, but its approval paths can authorize destructive actions with weak request binding and exposed approval tokens.
LLM: suspicious (high) · VirusTotal: · 29 May 2026