Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/securitytalent/bugskill-ai/cachedeceptionnpx skills add SecurityTalent/bugskill-ai --skill cachedeceptiongit clone --depth 1 https://github.com/SecurityTalent/bugskill-aiWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00058 | $0.04576 |
| Opus 5 | $0.00029 | $0.02288 |
| Sonnet 5 | $0.00012 | $0.00915 |
| Haiku 4.5 | $0.00006 | $0.00458 |
Grade A, and why
CacheDeception scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 652 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cache Deception Skill
Expert-level web cache exploitation for bug bounty hunting. Covers URL parsing discrepancies between CDNs and origin servers that enable cache deception (hijack sensitive data) and cache poisoning (store malicious payloads).
When to Activate
- "cache deception" → Arbitrary Web Cache Deception section
- "cache poisoning" → Arbitrary Web Cache Poisoning section
- "CDN bypass" → URL Discrepancies section
- "path confusion" → Delimiters & Normalization sections
- "static extension" → Static Extensions Exploitation
- "cache key" → Key Normalization section
Core Concepts
Web Cache Deception
Trick the cache into storing dynamic responses containing sensitive user data. Attacker creates malicious URL, victim clicks it, their authenticated response gets cached, attacker retrieves it.
Impact: Token theft, API key leakage, PII exposure, account takeover
Web Cache Poisoning
Store malicious payloads in cache under legitimate keys. All users requesting that resource receive the poisoned response.
Impact: Mass XSS, redirect hijacking, full site defacement
The Key Insight
CDNs and origin servers parse URLs differently. Exploit these discrepancies to:
- Make cache think a dynamic response is static (deception)
- Make cache store response under a different key than intended (poisoning)
URL Discrepancies
Delimiters
Different servers treat different characters as path delimiters:
| Server/Framework | Delimiter | Example |
|---|---|---|
| Spring (Java) | ; (semicolon) |
/myAccount;var=val → /myAccount |
| Ruby on Rails | . (dot) |
/myAccount.css → /myAccount (default view) |
| OpenLiteSpeed | %00 (null byte) |
/myAccount%00xxx → /myAccount |
| Nginx (rewrite) | %0a (newline) |
/myAccount%0axxx → /myAccount |
CDN Delimiter Behavior
| CDN | Uses # as delimiter? |
Uses ; as delimiter? |
|---|---|---|
| CloudFlare | NO | NO |
| CloudFront | YES | NO |
| GCP | ERROR | NO |
| Azure | YES | NO |
| Imperva | NO | NO |
| Fastly | NO | NO |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 652 lines · 58 tokens per session scan A 1867e6f30016
CacheDeception is a skill published in the GitHub repository SecurityTalent/bugskill-ai (5 stars, last pushed 16d ago), licensed MIT. It adds 58 tokens to every session and 4,576 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
srt-whiteboard-animation
将 SRT 字幕做成暖米黄纸张底的白板手绘动画：读字幕→输出配图策略→确认后生成统一风格线稿→按叙事语义标注分区→预览台调整→渲染 MP4。编排沿用分区遮罩揭示（annotation.json / sequence / startMs / protectedRegions），但每个区域内的落墨换成 stream 的连续笔迹（骨架/网格 ink→color）。当用户提供 SRT 字幕并要求"字幕做成白板手绘/流式笔迹视频""SRT 生成白板动画""按字幕分镜画手绘"时触发。.
user-research-cookiy
End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design, usability studies, participant recruitment…
seo
Deterministic LLM-first SEO audits for websites, blog posts, and GitHub repositories. Use this when the user asks to "perform SEO analysis", "run SEO audit", "analyze SEO", "check technical SEO", "review schema", "Core Web Vitals", "E-E-A-T", "hreflang", "GEO", "AEO", or GitHub repository SEO optimization. For…
playwright-best-practices
Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions…
open-map-stack
Use textual agent instructions for GIS and geospatial work: source discovery and provenance, vector/raster/point-cloud pipelines, CRS and metric analysis, spatial SQL, routing and isochrones, QGIS projects, tile generation, and web maps. Use advanced tools and formats such as OSM, Overture, STAC, Sentinel/Landsat…
globalpercent
GlobalPercent — build a global-macro-probability panel for an investment research system. Merges public probability data from prediction markets (Polymarket + Kalshi), classifies every market into macro modules (monetary policy / macro economy / AI / etc.), and shows the whole market's expected-probability state at a…