PurpleAILAB/Decepticon - 第 4 页

misinformation

Hunt LLM misinformation / overreliance (OWASP LLM09:2025) — confident-but-wrong outputs that flow into downstream automated decisions, compliance reports, customer communications, or autonomous code commits without verification.

原文语言：英语

path-traversal

Hunt directory traversal and archive traversal (ZipSlip/TarSlip) from user input to filesystem operations.

原文语言：英语

pattern-exhaustion

Systematic pattern exhaustion methodology. Load after finding any confirmed vulnerability to search for all instances of the same root cause pattern across the codebase.

原文语言：英语

prompt-injection

Hunt LLM prompt injection and tool-call hijacking in modern AI-integrated applications (CWE-1427). Covers indirect injection via RAG, tool abuse, exfiltration chains, and jailbreak-to-RCE pivots on agentic systems.

原文语言：英语

prototype-pollution

Hunt JavaScript prototype pollution (CWE-1321) — the 2023-2026 meta-vulnerability that chains into RCE, auth bypass, and SSRF on most Node.js stacks.

原文语言：英语

sensitive-information-disclosure

Hunt LLM sensitive-information disclosure (OWASP LLM02:2025) — leakage of PII, secrets, internal source, model details, and other-tenant data through model outputs, training-data extraction, or retrieval-side joins.

原文语言：英语

sql-injection

Hunt SQL injection (CWE-89) via source-level taint tracking. Covers string concat, format-string, ORM raw queries, second-order injection, and NoSQL injection in MongoDB/DynamoDB.

原文语言：英语

ssrf

Hunt Server-Side Request Forgery (CWE-918) through taint analysis from user-controlled URLs to HTTP client sinks. Covers cloud metadata pivoting, DNS rebinding, gopher smuggling, and the IMDSv1 → IAM role chain that turns SSRF into RCE.

原文语言：英语

ssti

Hunt server-side template injection across Jinja2/Twig/Freemarker/Velocity/Handlebars and validate progression from expression injection to code execution.

原文语言：英语

system-prompt-leakage

Hunt LLM system-prompt leakage (OWASP LLM07:2025) — exfiltration of the privileged system prompt revealing internal rules, secrets baked in, tool inventory, and business logic that should not be client-visible.

原文语言：英语

trust-boundary-analysis

Trust boundary mapping and startup sequence audit for developer tools, CLI apps, and plugin systems. Load when the target is a developer tool, CLI, IDE extension, or any application that loads config from the current directory.

原文语言：英语

unbounded-consumption

Hunt LLM unbounded consumption (OWASP LLM10:2025) — denial-of-wallet and denial-of-service against LLM endpoints via unrestricted prompt size, runaway tool loops, expensive model selection, and unauthenticated fan-out.

原文语言：英语

vector-and-embedding-weaknesses

Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.

原文语言：英语

xxe

Hunt XML External Entity flaws in parsers and validate file read / SSRF impact with strict negative controls.

原文语言：英语

references

External knowledge integration — HackerOne reports, PayloadsAllTheThings, Book of Secret Knowledge, CVE PoC corpora, bug bounty methodologies, and reference pentest agent architectures. Use these to calibrate, look up payloads, and accelerate research.

原文语言：英语

kill-chain-analysis

Kill chain analysis and attack path decision-making — findings analysis, attack vector selection, target prioritization, phase transitions.

原文语言：英语

detector-overview

Stage 2 vulnerability detector playbook. Reads source around CANDIDATE nodes and promotes real bugs to VULNERABILITY + HYPOTHESIS. Read-only. Load at detector-agent startup.

原文语言：英语

exploiter-overview

Stage 5 exploit construction playbook. Weaponizes validated primitives into multi-step chains that reach crown jewels. Load at exploiter-agent startup.

原文语言：英语

patcher-overview

Stage 4 patch generation playbook. Minimal diffs for validated findings with mandatory patch_verify. Load at patcher-agent startup.

原文语言：英语

scanner-overview

Stage 1 broad-spectrum scanner playbook. Sharded sweep over very large codebases producing CANDIDATE nodes for the Detector to reason about. Load at scanner-agent startup.

原文语言：英语

bounty-report-formatter

Bug bounty report formatting for HackerOne, Bugcrowd, Immunefi, and GitHub Security Advisories. Load after validate_finding succeeds and the finding needs to be submitted to a bounty program.

原文语言：英语

vulnresearch-orchestrator

Five-stage modular vulnerability pipeline orchestrator. Delegates scan → detect → verify → patch → exploit through OPPLAN objectives. Load at orchestrator startup.

原文语言：英语

benchmark

Benchmark mode marker — engagement objective is flag capture. Generic engagement rules apply unchanged.

原文语言：英语

supply-chain

Hunt LLM supply-chain compromise (OWASP LLM03:2025) — malicious or backdoored models, datasets, adapters, plugins, MCP servers, and tokenizer / framework dependencies that ship inside an AI-integrated product.

原文语言：英语

iot-overview

Use when the engagement target is IoT, embedded Linux, RTOS, or any device reachable via UART/JTAG/SWD or by extracting its firmware. Covers firmware acquisition, binwalk extraction, filesystem mounting, default-credential hunting, bootloader attacks,…

原文语言：英语

pentest-task-tree

Iterative PTT (Penetration Testing Tree) session reasoning — build, update, and traverse a live numbered task tree to drive LLM-guided pentest decisions across a full session.

原文语言：英语

access-control

Missing modifiers, wrong msg.sender checks, default-public functions, missing onlyOwner / onlyRole / onlyDAO authorization.

原文语言：英语

flash-loan

Flash-loan exploit patterns — callback reentrancy, oracle amplification, governance attacks, unauthenticated callback handlers.

原文语言：英语

oracle-manipulation

Hunt single-block oracle manipulation — spot-price AMM oracles, manipulable TWAP, dependent calculations, missing staleness checks.

原文语言：英语

reentrancy

Hunt and validate reentrancy bugs — classic cross-function, same-function, read-only, and cross-contract variants.

原文语言：英语

signature-replay

Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.

原文语言：英语

contracts-overview

Smart contract audit lane — Solidity/EVM pattern scanner, Slither ingestion, Foundry PoC generation, DeFi attack playbooks.

原文语言：英语

upgradeable-proxy

Proxy upgrade patterns and their bugs — uninitialized implementation, storage slot collisions, selector clashes, unprotected upgrade auth.

原文语言：英语

aws-iam-enum

Enumerate AWS IAM policies, detect privilege escalation paths per Rhino Security Labs canonical 21 primitives.

原文语言：英语

imds-pivot

Pivot from SSRF or RCE to cloud Instance Metadata Service (IMDS) — extract IAM role creds, instance identity, user-data secrets.

原文语言：英语

k8s-pivot

Kubernetes attack playbook — service-account token theft, RBAC abuse, pod escape, hostPath mount abuse, kube-api-server pivoting.

原文语言：英语

s3-takeover

Detect and claim dangling S3 buckets referenced by subdomains (CNAME → s3 hostnames where bucket no longer exists).

原文语言：英语

terraform-state-leak

Exploit exposed Terraform state files — secrets, cloud creds, RDS passwords, IAM keys, and infrastructure topology in plain JSON.

原文语言：英语

adcs-esc1

Exploit Active Directory Certificate Services ESC1 — vulnerable template allows arbitrary SAN, enabling user impersonation up to domain admin.

原文语言：英语

asrep-roasting

Request AS-REP for accounts with DONT_REQ_PREAUTH set and crack offline — like kerberoast but no auth required.

原文语言：英语