SKILLEMALL.ai
GitHub ↗ RU Sign in

CD sc-audit

Deep security audit of a smart-contract repo OR a live on-chain contract by address - detect Solidity, model the protocol invariants and trust boundaries first, run Slither (best-effort) plus a bounded agentic pass that hunts for a path breaking each invariant, triage, adversarially verify, prove with a fuzzer, and drive each finding through the shared responsible-disclosure routing. The dedicated contract arm split out of vuln-scanner.

aeonfun/aeon Agent Skills author: aeonfun 5 files body ≈ 17 347 tokens Open the sourcegithub.com↗ analyzed 67 min ago

Deep security audit of a smart-contract repo OR a live on-chain contract by address - detect Solidity, model the protocol invariants and trust boundaries…

As a process D 41/100 · Unfinished process — References files that are not bundled: scripts/notify_format.py

AnalyzerGitHubSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
80/100
safety, quality, tests
Safety 60%
97
Quality 40%
55
Run on models
none yet
Process rating
D
41/100
Unfinished process
References files that are not bundled: scripts/notify_format.py
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
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
  • low Exfiltration net-credential-use README.md:46
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    and use plain curl with $ETHERSCAN_API_KEY wherever the skill says ./secretcurl.
    security skill
  • low Risky intent intent-offensive-security SKILL.md:528
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    - **§A5.0** - read the repo's `SECURITY.md` (and the org-level `{owner}/.github` fallback). The designated intake wins over PVR. Do not trust a README "bug bounty coming soon" line - search the five p
    quoted

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 5. 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 ≈ 17347 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/notify_format.py
  • note edit-residue the text marks something as outdated (lines 134, 242, 677): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 41/100

Will not run. References files that are not bundled: scripts/notify_format.py
  • 0Tools and files. 1 referenced file(s) missing: scripts/notify_format.py
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 17347 tokens: crowds the task out of the window
  • 30Running it twice. 26 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 62 steps, 1 vague phrases
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 18 top-level sections: this looks like several domains in one skill
  • high The skill tells the model to perform an irreversible action with no human approval
  • low The response is described with custom markup (23 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
  • -5TODO / placeholder text left in the skill
  • +1No license
  • +2Single-language instructions
  • +3Description length 440: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 62 items
  • +4Has examples (19 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.