SKILLEMALL.ai
GitHub ↗ RU Sign in

CA wei-devils-advocate

Stress-test ideas using multiple LLMs in adversarial roles to generate counterarguments, cross-check reasoning, and expose hidden risks and failure modes. 易找茬：通过多模型对抗式分析与交叉验证，从不同视角生成反对意见并揭示潜在风险。

Not recommendedcritical or high security findings
ClawHub Agent Skills author: Wei Han v1.0.0 MIT-0 21 files body ≈ 1 772 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process A 80/100 · Runs to the end — weak spots: running it twice, progress reporting

GeneratorAI and agentsInfrastructuretype 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
62/100
safety, quality, tests
Safety 60%
57
Quality 40%
70
Run on models
none yet
Process rating
A
80/100
Runs to the end
Progress reporting w 2
0
Running it twice w 4
30
When it triggers w 12
50
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.

Instruction override
If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

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.

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.
  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 · 10

  • high Instruction override en-ignore-previous scripts/agent.ts:286
    Instruction-override phrase ("ignore previous instructions")
    /ignore previous instructions/gi,
Medium and low: 9
  • medium Exfiltration net-redirectable-api-key scripts/clients/bailian.ts:148
    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 Exfiltration net-redirectable-api-key scripts/clients/openai_compliant.ts:178
    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 Exfiltration net-redirectable-api-key scripts/clients/openrouter.ts:132
    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-pipe-to-shell-known-host SKILL.md:49
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -fsSL https://bun.sh/install | bash
  • low Secrets in code secret-high-entropy-token package-lock.json:26
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…7pY+zoMV…h0x/Ptw8…8dg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:43
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…b00+Gxjx…zRc/oZwU…hzA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:111
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-vHk/hA7/1Ack…wbo+jaSh…Gtl+A5zq…HFg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:145
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Dsc+j03S…0oA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:434
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…NS8+tHW7…WOF+PEzk…X4Q==",
    detector

Files scanned: 20. 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")
  • note frontmatter-key unknown frontmatter key "execution"
  • note frontmatter-key unknown frontmatter key "env"

Process rating: all ten parameters 80/100

  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 1 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Tools and files. No external tools needed
  • 100Steps. 38 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1772 tokens
  • low 12 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)
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 194: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 38 items
  • +3Output format is stated explicitly
  • +4Has examples (6 code blocks)

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

External checks

ClawHub: clean
This is a coherent multi-model critique skill, but users should know it sends prompts to external model providers and saves plaintext reports locally.
LLM: benign (high) · VirusTotal: · 29 May 2026