BB logic-hunter
Hard-core logic verification and evidence tracing tool based on the "Golden Triangle" knowledge mining framework
As a process B 67/100 · Nearly there — weak spots: when it triggers, failures and branches, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 8
✓ No critical or high findings
Medium and low: 8
-
low Risky intent
intent-offensive-securityREADME.md:13Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Red Team Challenge** — Automatically finds survivor bias, reverse causality, and other logical vulnerabilities
-
low Risky intent
intent-offensive-securityREADME.md:78Offensive-security / dual-use content (legitimate for authorised testing; review intended use)🔴 Red Team Attack Points
-
low Risky intent
intent-offensive-securityREADME.md:125Offensive-security / dual-use content (legitimate for authorised testing; review intended use)🔴 Red Team Attack Points
-
low Risky intent
intent-offensive-securitySKILL.md:23Offensive-security / dual-use content (legitimate for authorised testing; review intended use)4. **Red Team Challenge**: Simulate opponent role to find "survivor bias" or "reverse causality" in current evidence chain
-
low Risky intent
intent-offensive-securitySKILL.md:68Offensive-security / dual-use content (legitimate for authorised testing; review intended use)🔴 Red Team Attack Points
-
low Risky intent
intent-offensive-securitySKILL.md:106Offensive-security / dual-use content (legitimate for authorised testing; review intended use)4. Execute red team attack to identify vulnerabilities
-
low Risky intent
intent-offensive-securitySKILL.md:120Offensive-security / dual-use content (legitimate for authorised testing; review intended use)4. Red team attack: Find survivor bias, reverse causality
-
low Risky intent
intent-offensive-securitySKILL.md:134Offensive-security / dual-use content (legitimate for authorised testing; review intended use)🔴 Red Team Attack Points
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 67/100
- 0Failures and branches. Linear process with no failure handling
- 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
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1036 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)
- +3Description length 112: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 20 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.
External checks
ClawHub: clean
Logic Hunter is a coherent fact-checking skill that uses search and a local scoring helper without evidence of hidden, destructive, or privileged behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026