SKILLEMALL.ai
GitHub ↗ RU Sign in

DC pulse-board

Universal operational digest for agent skill stacks. Every scheduled skill logs its outcome with log-append.sh. Twice daily, digest-agent.sh reads the log, composes a human-readable summary via your configured OpenClaw agent, delivers it to Telegram/Discord/log, and clears. Falls back to mechanical format if the agent call fails. install.sh handles everything interactively in one run. plug.sh wires any skill's cron job in one command.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: LittleJakub v1.1.3 MIT-0 10 files · 6 scripts body ≈ 1 162 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

GeneratorTelegramDiscordAI and agentstype 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
D
51/100
safety, quality, tests
Safety 60%
37
Quality 40%
72
Run on models
none yet
Process rating
C
59/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
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.
  2. 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 · 13

  • high Dangerous commands cmd-persistence plug.sh:152
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    done < <(crontab -l 2>/dev/null | grep "pulse-board:" || true)
  • high Dangerous commands cmd-persistence plug.sh:183
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    done < <(crontab -l 2>/dev/null || true)
Medium and low: 11
  • medium Dangerous commands cmd-persistence install.sh:279
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    EXISTING_CRON="$(crontab -l 2>/dev/null || true)"
    code literal
  • medium Exfiltration net-credential-use install.sh:329
    Credential used in a network call (verify the destination is the intended service)
    if confirm "Append missing keys to $SECRETS_ENV?"; then
  • medium Dangerous commands cmd-persistence unplug.sh:50
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    EXISTING_CRON="$(crontab -l 2>/dev/null || true)"
    code literal
  • medium Dangerous commands cmd-persistence unplug.sh:53
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)
    echo "$EXISTING_CRON" | grep -v "pulse-board:$SKILL_SAFE" | crontab -
    detector
  • low Exfiltration exfil-webhook-url deliver.sh:52
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    curl -sf -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \
    placeholder
  • low Exfiltration net-credential-use deliver.sh:52
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -sf -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \
    vendor-host
  • low Dangerous commands cmd-cron-mention install.sh:279
    Mentions editing / listing crontab (string literal in code, not executed)
    EXISTING_CRON="$(crontab -l 2>/dev/null || true)"
    code literal
  • low Dangerous commands cmd-cron-mention plug.sh:152
    Mentions editing / listing crontab
    done < <(crontab -l 2>/dev/null | grep "pulse-board:" || true)
  • low Dangerous commands cmd-cron-mention plug.sh:183
    Mentions editing / listing crontab
    done < <(crontab -l 2>/dev/null || true)
  • low Exfiltration exfil-webhook-url SKILL.md:55
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    - **Telegram:** `POST https://api.telegram.org/bot<token>/sendMessage`
    placeholder
  • low Dangerous commands cmd-cron-mention unplug.sh:50
    Mentions editing / listing crontab (string literal in code, not executed)
    EXISTING_CRON="$(crontab -l 2>/dev/null || true)"
    code literal

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")

Process rating: all ten parameters 59/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 9 mutating operations with no state check
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 10 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1162 tokens
  • 100Progress reporting. Reports progress
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

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 438: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 10 items
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.

External checks

ClawHub: clean
Pulse Board is a disclosed cron digest tool, with real privacy considerations around logs but no artifact-backed malicious or deceptive behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026