SKILLEMALL.ai
RU Sign in

AC adversarial-code-review

Multi-perspective adversarial code review with git-isolated worktrees. Two reviewers (Architect + Inspector), cross-validation, and synthesis report. The synthesis is the final arbiter — its verdict takes priority over individual reviewer outputs.

ClawHub Agent Skills author: chpomob v0.1.0 MIT-0 36 files · 1 script body ≈ 3 546 tokens Open the sourceclawhub.ai↗ analyzed 34 h ago

Multi-perspective adversarial code review with git-isolated worktrees.

As a process C 52/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency

AnalyzerPersonal productivitytype 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
A
91/100
safety, quality, tests
Safety 60%
93
Quality 40%
89
Run on models
none yet
Process rating
C
52/100
Has gaps
Inputs and preconditions w 11
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

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

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

    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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:25
      Pipe-to-shell installer from a well-known host (still executes remote code)
      curl -fsSL https://raw.githubusercontent.com/chpomob/adversarial-code-review/main/scripts/install.sh | bash
    • low Dangerous commands cmd-eval-dynamic references/codex-claude-hardware-review.md:61
      Dynamic code execution from decoded/untrusted input (quoted — discussed, not commanded)
      python3 -c "exec(open('scripts/adversarial_review.py').read().split('if __name__')[0]); import os; f=_list_tree('.'); print(f'{len(f)} files, {sum(os.path.getsize(p) for p in f):,} chars')"
      quoted
    • low Dangerous commands cmd-pipe-to-shell-known-host scripts/install.sh:4
      Pipe-to-shell installer from a well-known host (still executes remote code) (code comment)
      #   Bootstrap (from anywhere):  curl -fsSL https://raw.githubusercontent.com/chpomob/adversarial-code-review/main/scripts/install.sh | bash
      comment

    Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 52/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 8 mutating operations with no state check
    • 40Consistency. Frontmatter name (adversarial-code-review) differs from the folder (adversarial-code-review-2)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 85Steps. 36 steps, 1 vague phrases
    • 100Execution cost. Instruction body is 3546 tokens
    • 100Progress reporting. Reports progress
    • low The response is described with custom markup (3 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)
    • -31 of 3 scripts are never mentioned in SKILL.md
    • +2Single-language instructions
    • +3Description length 247: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 36 items
    • +3Output format is stated explicitly
    • +4Has examples (5 code blocks)
    • +4Reference files are cited in the instructions (1 of 22)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: suspicious
    The core code-review workflow is coherent, but the skill includes under-scoped high-impact install, sandbox-bypass, and credentialed quota-checking behavior that users should review carefully before installing.
    LLM: suspicious (high) · 3 Aug 2026