SKILLEMALL.ai
GitHub ↗ RU Sign in

CB nex-life-logger

Track computer activity (browser history, active windows, YouTube videos) locally and query it with AI. All activity data stays on your machine. LLM features require explicit user configuration. Ask your agent what you were doing at any time.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Nex AI v1.1.0 MIT-0 17 files · 1 script body ≈ 2 237 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, progress reporting

ReferenceYouTubeAI and agentsMedia and videoInfrastructuretype 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
72/100
safety, quality, tests
Safety 60%
62
Quality 40%
88
Run on models
none yet
Process rating
B
71/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Tools and files w 18
60
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.

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

  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 · 5

  • high Dangerous commands cmd-persistence setup.sh:179
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST"
Medium and low: 4
  • medium Exfiltration net-redirectable-api-key lib/config.py:49
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Dangerous commands cmd-persistence nex-life-logger.py:646
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    plist = os.path.expanduser("~/Library/LaunchAgents/com.nexai.life-logger.plist")
    code literal
  • medium Dangerous commands cmd-persistence nex-life-logger.py:662
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    plist = os.path.expanduser("~/Library/LaunchAgents/com.nexai.life-logger.plist")
    code literal
  • medium Dangerous commands cmd-shell-rc setup.sh:109
    Writes to a shell startup file
    echo "  Add this to your ~/.bashrc or ~/.zshrc"

Files scanned: 17. 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 71/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 33 steps
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2237 tokens
  • 100Running it twice. Mutating operations check current state

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)
  • +2Single-language instructions
  • +3Description length 242: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 33 items
  • +3Output format is stated explicitly
  • +4Has examples (11 code blocks)
  • +1License stated

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

External checks

ClawHub: suspicious
This is a real life-logging tool, but it starts continuous activity monitoring and understates some sensitive data and network behavior.
LLM: suspicious (high) · VirusTotal: · 29 May 2026