BD hunt-cache-poison
Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session-token cache deception, Akamai hop-by-hop smuggling → server-side edge poisoning, and Kettle's 2024 path-normalization WCD against Cloudflare/Fastly/GCP. Host/X-Forwarded-Host injection that reaches app logic (reset-link poisoning, routing SSRF, OAuth issuer) is owned by hunt-host-header; this skill owns the case where the poisoned response is CACHED and served to other users. Use when hunting cache poisoning, Web Cache Deception, CDN-fronted apps.
Hunting skill for cache poison vulnerabilities.
As a process D 42/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use)description: Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via
-
low Risky intent
intent-offensive-securitySKILL.md:17Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Asset CDNs** (JS/CSS delivery) — XSS payload delivery at scale
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5524 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "sources" - note
frontmatter-keyunknown frontmatter key "report_count"
Process rating: all ten parameters 42/100
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Execution cost. Instruction body is 5524 tokens
- 85Steps. 65 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 tags): a typed call is more reliable
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
- +1No license
- +2Single-language instructions
- +3Description length 732: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 65 items
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.