SKILLEMALL.ai

AC attacker

Attack any target (skill, design, argument, code, KB) with a FRESH independent attacker rotating five lenses; coverage-first strike, then PROVE-OR-FLAG adjudication (findings vs flags); never fixes. A different-vendor attacker buys stronger independence. Use-when: "red-team/break this", "$attacker". Do-NOT: fix or edit the target.

ClawHub Agent Skills author: VincentJiang06 v0.7.0 MIT-0 15 files body ≈ 2 866 tokens Open the sourceclawhub.ai analyzed 36 h ago

Attack any target (skill, design, argument, code, KB) with a FRESH independent attacker rotating five lenses; coverage-first strike, then PROVE-OR-FLAG…

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSoftware developmenttype and topics are labelled automatically from the skill text
JSON
Technical rating
A
97/100
safety, quality, tests
Safety 60%
100
Quality 40%
92
Run on models
none yet
Process rating
C
54/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

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 · 0

    ✓ No critical or high findings

    Files scanned: 15. 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 54/100

    • 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. 6 mutating operations with no state check
    • 40Result and completion. Does not say what the result is
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web, git) that frontmatter does not declare
    • 100Steps. 24 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2866 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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

    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 2 example trigger phrases
    • +3Description length 332: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 24 items
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

    External checks

    ClawHub: clean
    This is a disclosed red-team review skill that asks agents to critique targets and record findings, without evidence of hidden data access, destructive behavior, or exfiltration.
    LLM: benign (high) · VirusTotal: · 1 Aug 2026