SKILLEMALL.ai

BF dcl-skill-auditor

Scan any ClawHub skill before installing it. 534 out of 3,984 ClawHub skills contained critical vulnerabilities — credential theft, prompt injection, data exfiltration. Snyk Research, 2026. DCL Skill Auditor analyzes SKILL.md, scripts, and manifests against 30+ known attack patterns, optionally backed by a real, paid baseline-safety check via the live DCL Trust Oracle MCP server (x402, USDC on Base), and returns a structured PASS / WARN / BLOCK verdict with a cryptographic audit proof. Use this skill before every new install, on skill updates, or in any agent pipeline that requires a pre-execution security checkpoint. Part of the Leibniz Layer™ security suite by Fronesis Labs alongside DCL Policy Enforcer, DCL Prompt Firewall, and DCL Semantic Drift Guard.

ClawHub Agent Skills author: Dari Rinch v1.0.3 MIT-0 2 files body ≈ 3 367 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 51/100 · Will not run — References files that are not bundled: scripts/run.sh:17

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
80
Quality 40%
81
Run on models
none yet
Process rating
F
51/100
Will not run
References files that are not bundled: scripts/run.sh:17
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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.

Instruction override 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 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.

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. 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 · 12

✓ No critical or high findings

Medium and low: 12
  • medium Instruction override en-ignore-previous SKILL.md:57
    Instruction-override phrase ("ignore previous instructions") (documentation of a security skill)
    - Instructions to ignore or override system prompts
    security skill
  • low Risky intent intent-offensive-security SKILL.md:64
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Reverse shell signatures (`/dev/tcp`, `nc -e`, `bash -i`)
  • low Risky intent intent-offensive-security SKILL.md:207
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - [ ] Reverse shell: `/dev/tcp/`, `nc -e /bin/bash`, `bash -i >&`
  • low Secrets in code secret-high-entropy-token SKILL.md:276
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "dcl_proof": "DCL-…a0e",
    quoted
  • low Secrets in code secret-high-entropy-token SKILL.md:295
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "dcl_proof": "DCL-…c05",
    quoted

A further 7 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: scripts/run.sh:17

Process rating: all ten parameters 51/100

Will not run. References files that are not bundled: scripts/run.sh:17
  • 0Tools and files. 1 referenced file(s) missing: scripts/run.sh:17
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 63 steps
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3367 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 11 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 766: enough signal without eating the budget
  • +4Structure: 31 headings
  • +3Step-by-step instructions: 63 items
  • +3Output format is stated explicitly
  • +4Has examples (10 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.

External checks

ClawHub: clean
This skill is a coherent security-auditing checklist with a clearly disclosed optional paid live check.
LLM: benign (high) · VirusTotal: · 27 Jul 2026