BD Rate Limit Audit
Missing rate limit detector for API codebases. Scans Express/Koa/Fastify/NestJS, FastAPI/Flask/Django, Go (gin/chi/echo), Spring Boot, and Ruby (Rack) for 10 classes of unprotected endpoints — auth routes open to brute force, payment endpoints with no throttle, email/SMS senders without limit (cost amplification), search routes with no query throttle, retry logic without backoff, admin endpoints without per-IP limiting, and more. Zero external dependencies. Works on directories or single files. CI fail-gate included.
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitySKILL.md:60Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| RL006 | HIGH | Admin endpoint without per-IP rate limiting | Privilege escalation via brute force |
detector
Files scanned: 2. 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) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7772 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 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
- 30Running it twice. 14 mutating operations with no state check
- 40Consistency. Frontmatter name (Rate Limit Audit) differs from the folder (phy-rate-limit-audit)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Execution cost. Instruction body is 7772 tokens
- 100Steps. 18 steps
- 100Failures and branches. 2 branches, has a failure section
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
- +2Single-language instructions
- +3Description length 522: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (4 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.