PurpleAILAB/Decepticon

PurpleAILAB/Decepticon

Skill Claude CodeCodex

Build and validate SSRF pivot chains toward metadata/infra control and final code execution impact.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

Build chains from XSS into account takeover or privileged action execution.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

Hunt OS command injection (CWE-78) — user input reaching shell, exec, or system calls. Covers argument-array bypasses, path confusion, and template-string injection in modern frameworks.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

Hunt LLM training-data and model poisoning (OWASP LLM04:2025) — adversarial inputs that bias future model behaviour through fine-tuning, RLHF, or continuous-learning loops.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

Hunt insecure deserialization (CWE-502) across Python pickle, Java ObjectInputStream / Jackson / SnakeYAML, .NET BinaryFormatter / DataContractJson, PHP unserialize, Ruby Marshal/YAML.load, and Node.js vm. Direct path to unauthenticated RCE.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

Hunt LLM excessive agency (OWASP LLM06:2025) — agentic systems granted too many tools, too broad permissions per tool, or unsupervised authority to act on the user / business behalf, producing financial loss, data loss, or destructive operations from a single bad token.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

Hunt Insecure Direct Object Reference (CWE-639) — missing authorization checks on object IDs. Covers horizontal vs vertical privilege escalation, UUID vs integer guessing, and GraphQL introspection-driven IDOR discovery.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

Hunt improper LLM output handling (OWASP LLM05:2025) — downstream code that trusts unstructured model output and renders / executes / shells it without sanitisation, producing XSS, SSRF, SQL injection, RCE, and SSTI via the model channel.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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.

PurpleAILAB/Decepticon

Skill Claude Code

Extract a functional clone of a black-box ML model via prediction API queries, and infer whether specific records were in the training set (membership inference).

PurpleAILAB/Decepticon

Skill Claude Code

Authorized patch-diff workflow for deriving and validating vulnerability variants from a known vulnerable-to-fixed source change.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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

PurpleAILAB/Decepticon

Skill Claude Code

Hunt ReDoS (CWE-1333, Catastrophic Backtracking) — identify regexes with nested quantifiers or overlapping alternation that cause super-linear matching time, trace tainted input paths to regex sinks, demonstrate timing PoC, and validate with response-time delta. Covers PCRE/RE2/V8/Python re engine differences.…

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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.

PurpleAILAB/Decepticon

Skill Claude CodeCodex

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.

PurpleAILAB/Decepticon

Skill Claude Code

ANY.RUN Threat Intelligence Lookup workflow — query hashes, domains, IPs, and behavioral indicators against ANY.RUN's sandbox corpus. Covers TI Lookup query syntax, search operators, free tier constraints, result correlation with engagement findings, and integration with sandbox analysis.

PurpleAILAB/Decepticon

Skill Claude Code

Automated IOC extraction from threat reports, logs, and unstructured text — parse hashes, IPs, domains, URLs, email addresses, and CVEs. Covers regex-based extraction, defanging/refanging, bulk hash lookup, IOC deduplication, YARA rule generation from IOCs, and STIX/TAXII formatting for sharing.