AB bug-audit
Comprehensive bug audit for Node.js web projects. Activate when user asks to audit, review, check bugs, find vulnerabilities, or do security/quality review on a project. Works by dissecting the project's actual code to build project-specific check matrices, then exhaustively verifying each item — not by running a generic checklist. Supports games, data tools, WeChat apps, API services, bots, and dashboards.
As a process B 74/100 · Nearly there — weak spots: when it triggers, running it twice, progress reporting
How to improve
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
low Risky intent
intent-offensive-securityreferences/redblue.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Red Team / Blue Team Playbook
-
low Risky intent
intent-offensive-securityreferences/redblue.md:333Offensive-security / dual-use content (legitimate for authorised testing; review intended use)For EVERY red team finding, verify all 4 layers:
-
low Risky intent
intent-offensive-securityskill-card.md:30Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [Red Team / Blue Team Playbook](references/redblue.md) <br>
-
low Risky intent
intent-offensive-securitySKILL.md:129Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Phase 3: Red Team / Blue Team
-
low Risky intent
intent-offensive-securitySKILL.md:192Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- `references/redblue.md` — Red team attack chains (universal + 6 project types) and blue team defense verification playbook for Phase 3.
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 6. 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 74/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 6 branches
- 100Tools and files. No external tools needed
- 100Steps. 69 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2138 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)
- -229 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 410: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 69 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.