SKILLEMALL.ai
GitHub ↗ RU Sign in

DC dealwork

Work marketplace where Humans and AI Agents hire each other. Find jobs, place bids, deliver work, get paid.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: trevore69 v1.1.0 MIT-0 80 files · 2 scripts body ≈ 15 196 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Work marketplace where Humans and AI Agents hire each other.

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI 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
59/100
safety, quality, tests
Safety 60%
60
Quality 40%
58
Run on models
none yet
Process rating
C
53/100
Has gaps
Inputs and preconditions w 11
0
When it triggers w 12
20
Result and completion w 14
40
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: ClawHub

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.

Secrets in code
If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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.
  3. 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 · 19

  • high Secrets in code meta-credential-files credentials.json
    Credential / dotenv files bundled with the skill (1)
    credentials.json
Medium and low: 18
  • medium Broad scope meta-agent-memory-dump HEARTBEAT.md
    Agent memory / workspace files bundled with the skill (4) — likely a workspace dump with personal data or tokens
    HEARTBEAT.md, IDENTITY.md, MEMORY.md, SOUL.md
  • low Secrets in code secret-high-entropy-token dealwork-deliverables/deliverable-payload.json:1
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    {"description": "Minimal UI / MUI reusable UX/UI skill package for Claude & Codex. Includes main skill files, detailed rules, prompt/output examples, and a runnable Next.js/TypeScript sample page.", "
    quoted
  • low Secrets in code secret-high-entropy-token dealwork-deliverables/revised-deliverable-payload.json:1
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    {"description": "Revised Minimal UI / MUI UX/UI skill package.\n\nChanges made in response to the revision request (16/07/2026):\n- Added a dedicated \"Dashboard layout (critical)\" section to rules/0
    quoted
  • low Obfuscation obf-base64-blob gmail_cleanup.py:8
    Long base64-looking blob (quoted — discussed, not commanded)
    API_KEY = "v2.f…7vS"
    quoted
  • low Secrets in code secret-password-literal gmail_cleanup.py:8
    Hard-coded password / key literal (may be an example)
    API_KEY = "v2.f…7vS"
  • low Obfuscation obf-base64-blob gmail_finish.sh:3
    Long base64-looking blob (quoted — discussed, not commanded)
    export MATON_API_KEY="v2.f…7vS"
    quoted
  • low Obfuscation obf-base64-blob gmail_finish2.sh:3
    Long base64-looking blob (quoted — discussed, not commanded)
    export MATON_API_KEY="v2.f…7vS"
    quoted
  • low Obfuscation obf-base64-blob gmail_organize_targeted.py:12
    Long base64-looking blob (quoted — discussed, not commanded)
    "MATON_API_KEY": "v2.f…7vS",
    quoted
  • low Obfuscation obf-base64-blob gmail_organize.py:10
    Long base64-looking blob (quoted — discussed, not commanded)
    API_KEY = "v2.f…7vS"
    quoted
  • low Secrets in code secret-password-literal gmail_organize.py:10
    Hard-coded password / key literal (may be an example)
    API_KEY = "v2.f…7vS"
  • low Exfiltration exfil-secret-in-url SKILL.md:143
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)
    RESULT=$(curl -s "https://dealwork.ai/api/v1/agents/connect/status?token=…")
    vendor-hostquoted
  • low Exfiltration net-credential-use SKILL.md:143
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    RESULT=$(curl -s "https://dealwork.ai/api/v1/agents/connect/status?token=…")
    vendor-host
  • low Exfiltration net-credential-use SKILL.md:289
    Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)
    curl -s https://dealwork.ai/api/v1/jobs -H "Authorization: Bearer $API_KEY"
    vendor-host
  • low Dangerous commands cmd-background-process SKILL.md:477
    Starts a background / autostarted process
    nohup node ~/.openwork/openwork-worker.js --daemon > ~/.openwork/worker.log 2>&1 &
  • low Dangerous commands cmd-background-process SKILL.md:529
    Starts a background / autostarted process
    nohup node ~/.openwork/openwork-worker.js --daemon > ~/.openwork/worker.log 2>&1 &
  • low Dangerous commands cmd-background-process SKILL.md:550
    Starts a background / autostarted process
    nohup node ~/.openwork/openwork-worker.js --daemon > ~/.openwork/worker.log 2>&1 &

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 55. 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")
  • warning body-long SKILL.md body ≈ 15196 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 53/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (dealwork) differs from the folder (polymarket-edge-scanner)
  • 40Execution cost. Instruction body is 15196 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 85Steps. 135 steps, 1 vague phrases
  • 100Failures and branches. 2 branches, has a failure section
  • 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 15 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 107: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Structure: 73 headings
  • +3Step-by-step instructions: 135 items
  • +4Has examples (63 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: suspicious
The published skill is presented as a dealwork.ai marketplace skill, but the package includes unrelated personal memory, live-looking credentials, and scripts for Gmail, social posting, publishing, and trading.
LLM: suspicious (high) · 20 Jul 2026