SKILLEMALL.ai
RU Sign in

BC clawdtalk-client

ClawdTalk — Voice calls, SMS, and AI Missions for Clawdbot

Not recommendedcritical or high security findings
ClawHub Agent Skills author: dcasem v2.0.5 18 files · 8 scripts body ≈ 8 491 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost

ProcedureInfrastructuretype 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
B
75/100
safety, quality, tests
Safety 60%
74
Quality 40%
76
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Execution cost w 6
40
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. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 README.md:93
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    @reboot cd ~/clawd/skills/clawdtalk-client && ./scripts/connect.sh start
Medium and low: 4
  • medium Exfiltration net-redirectable-api-key scripts/telnyx_api.py:39
    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
  • low Dangerous commands cmd-cron-mention README.md:92
    Mentions editing / listing crontab
    # Add to crontab (crontab -e):
  • low Dangerous commands cmd-background-process scripts/connect.sh:153
    Starts a background / autostarted process
    nohup node "$SCRIPT_DIR/ws-client.js" $SERVER_FLAG >> "$LOG_FILE" 2>&1 &
  • low Secrets in code secret-password-literal status.sh:63
    Hard-coded password / key literal (may be an example) (placeholder value)
    masked_key="${api_key:0:6}...${api_key: -4}"
    placeholder

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8491 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Execution cost. Instruction body is 8491 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 100Steps. 64 steps
  • 100Failures and branches. 8 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 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 38 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
  • +3Description length 58: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 72 headings
  • +3Step-by-step instructions: 64 items
  • +4Has examples (34 code blocks)
  • +3All 6 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious
This skill is disclosed as a voice/SMS bridge, but it gives remote call and message flows broad access to the user's main agent with weak approval boundaries.
LLM: suspicious (high) · VirusTotal: suspicious · 10 Sept 2026