SKILLEMALL.ai

BF benchmark-robustness-auditor

Offline, defensive robustness auditor for LLM benchmarks: n-gram exact + shingle-Jaccard paraphrase contamination, temporal pre/post-cutoff gaps, TS-Guessing above-chance detection, option-letter selection bias (chi2), few-shot curve noise, LLM-judge position/verbosity/rubric-echo bias and hidden-instruction payload detection, paired McNemar + Wilson + deterministic bootstrap for score comparisons, WORKED mitigations (permutation majority ensemble, blind content normalization), documented 0-100 severity formula, hash-chained per-target history ledger with trend deltas. Findings cite a STATIC 17-id exploit catalogue with explicit computable flags — invisible exploit classes are declared, never fabricated. 100% stdlib python3. NO network, NO telemetry. Defense/auditing only.

ClawHub Agent Skills author: orionshaowswmw v2.0.0 MIT-0 10 files body ≈ 895 tokens Open the sourceclawhub.ai analyzed 2 d ago

Offline, defensive robustness auditor for LLM benchmarks: n-gram exact + shingle-Jaccard paraphrase contamination, temporal pre/post-cutoff gaps, TS-Guessing…

As a process F 44/100 · Will not run — References files that are not bundled: scripts/benchscan.py

AnalyzerResearchtype and topics are labelled automatically from the skill text
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
100
Quality 40%
61
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: scripts/benchscan.py
Tools and files w 18
0
Result and completion w 14
0
Failures and branches w 10
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 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 · 0

✓ No critical or high findings

Files scanned: 0. 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 missing-ref reference to a missing file: scripts/benchscan.py
  • note frontmatter-key unknown frontmatter key "topics"

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: scripts/benchscan.py
  • 0Tools and files. 1 referenced file(s) missing: scripts/benchscan.py
  • 0Result and completion. Does not say what the result is
  • 0Failures and branches. Linear process with no failure handling
  • 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
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 12 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 895 tokens

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
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 783: enough signal without eating the budget
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 12 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.

External checks

ClawHub: clean
This skill is a coherent offline benchmark-auditing tool; the flagged shell pattern is confined to its local self-test and does not show hidden or malicious behavior.
LLM: benign (high) · VirusTotal: · 6 Sept 2026