SKILLEMALL.ai
GitHub ↗ RU Sign in

CC Vigil

Front door to Vigil, the always-on monitoring layer: every subsystem and scheduled job logs events in one format, a five-minute tick routes them by severity to a text, the digest, or the dashboard, and this skill reads or feeds that log. USE WHEN what is going on, what's happening right now, anything I should know, vigil, vigil status, is the tick alive, heartbeat, post an event, log this to vigil, emit an event, pending digest, what got held, install vigil, vigil policy. NOT FOR filing a complaint about a system (Errata), standing questions and their answers (the Socrates ledger), or the vulnerability registry itself (Achilles).

Not recommendedcritical or high security findings
danielmiessler/Personal_AI_Infrastructure Agent Skills author: danielmiessler 6 files body ≈ 1 464 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Front door to Vigil, the always-on monitoring layer: every subsystem and scheduled job logs events in one format, a five-minute tick routes them by severity…

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureData and analyticsInfrastructureSecuritytype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
79/100
safety, quality, tests
Safety 60%
77
Quality 40%
82
Run on models
none yet
Process rating
C
56/100
Has gaps
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.

Exfiltration
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. 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 · 2

  • high Exfiltration intent-browser-credential-store SKILL.md:42
    Accesses a browser credential / cookie store
    - Local state: `~/.local/state/lifeos/vigil/` (outbox, sent ledger, adapter cursors, reader cursor, digest, last tick). Override with `VIGIL_STATE_DIR`.
Medium and low: 1
  • medium Dangerous commands cmd-persistence Setup.md:7
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    **macOS only.** The five-minute tick is a launchd agent (`InstallVigil.ts` writes `~/Library/LaunchAgents/com.lifeos.vigil.plist`), and texts go through Relay, which runs on a Mac with Messages. The e
    quoted

Files scanned: 6. 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)
  • note frontmatter-key unknown frontmatter key "evals"

Process rating: all ten parameters 56/100

  • 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
  • 30Running it twice. 3 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Steps. 15 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1464 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 637: enough signal without eating the budget
  • +4Structure: 6 headings
  • +3Step-by-step instructions: 15 items
  • +4Has examples (3 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.