CC hunt-xss
Hunting skill for xss vulnerabilities.
Hunting skill for xss vulnerabilities.
As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
The same skill appears in 2 more places: agentic-awesome-skills, agentic-awesome-skills
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 8
✓ No critical or high findings
Medium and low: 8
-
low Risky intent
intent-offensive-securityreferences/details.md:54Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Impact:** Privilege escalation from low-priv user to admin via stored XSS — attacker promotes themselves on the privileged user's behalf.
-
low Risky intent
intent-offensive-securityreferences/details.md:55Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- **Real shape:** GitLab/Jira/Confluence markdown-XSS-to-admin-priv-esc class; common payout pattern is High (privilege escalation severity bump over standalone stored XSS).
detector -
low Risky intent
intent-offensive-securityreferences/details.md:59Offensive-security / dual-use content (legitimate for authorised testing; review intended use)When you confirm XSS at A, immediately ask: what state-changing endpoint or token store does this JS now have access to? *Where does the payload run, and who sees it?* No payout multiplier is establis
-
low Risky intent
intent-offensive-securitySKILL.md:49Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Payment/financial flows** (`paypal.com`, checkout pages, currency converters) — XSS here enables credential harvesting and financial fraud at scale
-
low Risky intent
intent-offensive-securitySKILL.md:137Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. **Classify by type** — Determine if each reflection is Reflected (URL param → response), Stored (database → later rendering), or DOM-based (JS reads URL/storage → DOM sink). Each requires different
-
low Dangerous commands
cmd-eval-dynamicSKILL.md:308Dynamic code execution from decoded/untrusted input (documentation of a security skill)<svg onload=eval(atob('YWxlcnQoMSk='))> <!-- security-allowlist: documented payload technique reference, do not execute outside authorized scope -->security skill -
low Risky intent
intent-offensive-securitySKILL.md:355Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)An attacker discovered that a major payment platform's sign-in page reflected user-controlled input and was cached by the CDN layer. By sending a crafted request that poisoned the cache, the attacker
quoted
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-shortdescription under 40 chars: too little signal for triggering - warning
body-longSKILL.md body ≈ 5384 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "risk" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "source_repo" - note
frontmatter-keyunknown frontmatter key "source_type" - note
frontmatter-keyunknown frontmatter key "date_added" - note
frontmatter-keyunknown frontmatter key "license_source" - note
frontmatter-keyunknown frontmatter key "sources" - note
frontmatter-keyunknown frontmatter key "report_count" - note
edit-residuethe text marks something as outdated (lines 278, 316): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5384 tokens
- 100Steps. 67 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (19 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)
- +3Description length 38: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 67 items
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.