BF JWT Auth Audit
JWT and OAuth/OIDC security auditor. Decodes any JWT token (without verification) to inspect alg/exp/iss/aud/scope claims, detects the "alg:none" bypass vulnerability, expired or no-expiry tokens, overly broad OAuth scopes, JWT stored in localStorage (XSS theft risk), JWT in URL parameters (log leakage), missing issuer/audience validation in source code, hardcoded tokens in .env files, and weak HMAC secrets. Also scans source files for insecure token handling patterns: Bearer token logged, token compared with ==, auth bypass via role:admin in payload. Generates a severity-ranked report with exact code locations and fixes. Zero external API — pure local analysis. Triggers on "JWT audit", "token security", "auth security", "alg none", "OAuth scopes", "bearer token", "token expiry", "/jwt-audit".
As a process F 37/100 · Will not run — References files that are not bundled: ?:token|auth|jwt|access_token|bearer, token|access_token|jwt|auth_token|bearer, ?!process\.|os\.|getenv
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: JWT and OAuth/OIDC security auditor. Decodes any JWT token (withou… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5639 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ?:token|auth|jwt|access_token|bearer - warning
missing-refreference to a missing file: token|access_token|jwt|auth_token|bearer - warning
missing-refreference to a missing file: ?!process\.|os\.|getenv - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 37/100
- 0Tools and files. 3 referenced file(s) missing: ?:token|auth|jwt|access_token|bearer, token|access_token|jwt|auth_token|bearer, ?!process\.|os\.|getenv
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 40Consistency. Frontmatter name (JWT Auth Audit) differs from the folder (phy-jwt-auth-audit)
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5639 tokens
- 100Steps. 9 steps
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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)
- +3Description length 804: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (17 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 37.