BB AuthAudit
Authentication & authorization pattern analyzer — finds missing auth checks, insecure sessions, broken access control, CSRF gaps, and token handling vulnerabilities
As a process B 72/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, progress reporting
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Risky intent
intent-offensive-securityREADME.md:113Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| AZ-005 | Privilege escalation via parameter | High |
-
low Risky intent
intent-offensive-securitySKILL.md:53Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Identifies missing role checks, broken object-level authorization (BOLA), insecure direct object references (IDOR), missing permission verification, privilege escalation paths, hardcoded admin roles,
-
low Risky intent
intent-offensive-securitySKILL.md:254Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)- "Find privilege escalation paths"
quoted
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "triggers" - note
frontmatter-keyunknown frontmatter key "tools"
Process rating: all ten parameters 72/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 48 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2345 tokens
- 100Running it twice. Mutating operations check current state
- low 10 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)
- -34 of 5 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 164: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 48 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.
External checks
ClawHub: suspicious
AuthAudit mostly behaves like a local auth-security scanner, but its license-token parsing can run attacker-controlled code from a crafted license key.
LLM: suspicious (high) · VirusTotal: · 29 May 2026