SKILLEMALL.ai
GitHub ↗ RU Sign in

CC kami-fall-detection-cloud

Detect fall events from RTSP camera streams using KamiClaw cloud API. No local GPU needed.

ClawHub Agent Skills author: KamiVision v1.1.2 MIT-0 10 files · 1 script body ≈ 2 551 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency

IntegrationInfrastructuretype 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
74/100
safety, quality, tests
Safety 60%
77
Quality 40%
69
Run on models
none yet
Process rating
C
62/100
Has gaps
Inputs and preconditions w 11
0
When it triggers w 12
20
Consistency w 8
40
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.

Dangerous commands 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 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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 exfil-webhook-url discord_notifier.py:23
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "https://discord.com/api/webhooks/",
    quoted
  • medium Exfiltration exfil-webhook-url discord_notifier.py:24
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    "https://discordapp.com/api/webhooks/",
    quoted
  • medium Dangerous commands cmd-pipe-to-shell setup.sh:76
    Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)
    echo "     curl https://pyenv.run | bash"
    code literal
  • medium Exfiltration exfil-webhook-url telegram_notifier.py:20
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    TELEGRAM_API_URL = "https://api.telegram.org/bot"
    quoted
  • low Exfiltration exfil-webhook-url discord_notifier.py:37
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    (e.g., https://discord.com/api/webhooks/123456789/abcdefghijklmnop)
    placeholder
  • low Exfiltration exfil-webhook-url README.md:189
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    - For private chat: Message the bot, then visit `https://api.telegram.org/bot<TOKEN>/getUpdates`
    placeholder
  • low Exfiltration exfil-webhook-url README.md:212
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    "discord_webhook_url": "https://discord.com/api/webhooks/123456789/abcdefghijklmnop"
    placeholder

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

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "triggers"

Process rating: all ten parameters 62/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (kami-fall-detection-cloud) differs from the folder (kami-fall-detection)
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 35 steps
  • 100Failures and branches. 4 branches, has a failure section
  • 100Execution cost. Instruction body is 2551 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 top-level sections: this looks like several domains in one skill

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)
  • +3Description length 90: 120–800 characters recommended
  • -217 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 35 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
This skill mostly does what it claims, but it handles home-camera footage and credentials with several under-disclosed external data flows and an install script that can delete a conda environment without confirmation.
LLM: suspicious (high) · 10 Jun 2026