Security

yue-zhou1 Bundle

Audit randomness and nonce lifecycles: CSPRNG/DRBG initialization and reseeding, entropy availability, fork/clone/snapshot duplication, deterministic nonce derivation (RFC 6979, EdDSA), and reuse across retries, crashes, persistence, and concurrent state. Use when any secret-dependent random value's generation or lifetime is in question.

yue-zhou1 Bundle

Review Rust cryptographic code for implementation-level security bugs. Use when auditing constant-time behavior, secret zeroization, panic and overflow hazards, unsafe blocks, unchecked constructors, feature flags, or dependency hygiene in crypto crates.

yue-zhou1 Bundle

Audit threshold ECDSA implementations (GG18, GG20, CGGMP21, Lindell-style) for Paillier modulus validity, MtA/MtAwc range-proof gaps, share-conversion soundness, resharing and concurrent-session isolation, and identifiable-abort leakage. Use when reviewing multi-party ECDSA keygen, signing, or resharing.

yue-zhou1 Bundle

Audit folding scheme and IVC implementations for accumulator soundness, step circuit binding, cycle-of-curves correctness, and running instance completeness. Use when reviewing Nova, HyperNova, ProtoStar, or custom folding-based proof systems in Rust.

yue-zhou1 Bundle

Audit timing, cache, memory-access, and power-analysis leakage patterns, including compiler and feature-flag regressions that break constant-time assumptions.

yue-zhou1 Bundle

Audit shielded-pool and mixer protocol logic: nullifier derivation, uniqueness, and spent-set semantics; note/value commitments and ownership binding; deposit/withdraw front-running; and state-transition replay domains. Use when reviewing privacy-protocol design above the circuit and Merkle layers.

yue-zhou1 Bundle

Audit post-quantum signature implementations — ML-DSA (FIPS 204), SLH-DSA (FIPS 205), FN-DSA/Falcon (pending standardization), and stateful hash signatures XMSS/LMS/HSS (NIST SP 800-208) — for rejection-sampling correctness, hedged/deterministic signing modes, verification bound enforcement, and one-time-signature state management. Use when reviewing PQ signing, verification, or OTS index/state persistence.

yue-zhou1 Bundle

Audit Solidity, Vyper, or Huff proof-verifier contracts for pairing precompile misuse, missing scalar-field checks on public inputs, calldata decoding errors, and verification-key provenance or upgrade risks. Use when reviewing on-chain SNARK/STARK verifier contracts or EIP-196/197/2537 precompile call sites.

yue-zhou1 Bundle

Audit elliptic-curve, pairing, and BLS signature code for point-validation, subgroup, serialization, DST, and pairing-equation failures. Use when reviewing deserialization, `hash_to_curve`, aggregate verification, or batch pairing logic.

yue-zhou1 Bundle

Audit Fiat-Shamir transcript implementations for completeness, domain separation, challenge derivation order, and public input binding across interactive-to-non-interactive proof transforms.

yue-zhou1 Bundle

Audit Merkle tree implementations for second-preimage attacks, leaf-node domain separation, sparse tree edge cases, and proof verification soundness.

yue-zhou1 Bundle

Audit ZK-friendly hash functions (Poseidon, Rescue, MiMC, Pedersen) for parameter selection, sponge construction, domain separation, and algebraic attack resistance.

yue-zhou1 Bundle

Bridge validated audit findings into optional external formal-verification tooling (Ecne, Picus, Circomspect) with explicit environment checks, reproducible exports, and tool-scoped caveat capture.

yue-zhou1 Bundle

Audit Rust application code that uses Ethereum cryptography. Use when reviewing secp256k1/ECDSA usage, keccak/EIP-712 hashing, BN254/BLS12-381 precompile interaction, KZG/EIP-4844 patterns, or alloy/ethers-rs API usage.

hmbown Skill

Use Aqua Aura when the real threat is heat: escalating pressure, bursty contention, emotional overtemperature, or rapid-fire noise that is making clean operation impossible. Unlike a plain Aura that simply blanks weaker hits, Aqua Aura diffuses and cools them so Hermes can keep moving without matching the room's panic tempo.

hmbown Skill

Use Fire Aura when the real threat is not one decisive blow but a stream of low-grade interruptions, shallow objections, retry churn, or opportunistic pokes that keep stealing momentum. Fire Aura establishes an aggressive protective threshold: trivial contact gets burned away automatically so Hermes can stay on the offensive, while anything substantial still has to be named and handled honestly.

hmbown Skill

Use Curse Shield when Hermes should protect a surface in a way that makes contact linger on the attacker. The shield is not just there to absorb the next hit or throw an immediate counter; it tags hostile touch with a lasting penalty, mark, or contamination that follows the offender after impact. In practice, Curse Shield is for defended surfaces that impose audit burden, throttling, suspicion, reduced trust, quarantine, follow-up scrutiny, or another durable consequence on whatever keeps pressing into them.

arasz Bundle

Use when ai-badger's own machinery needs to be observed — "did that hook even run?", "enable debug logging", "why is the drift notice silent?", "turn on the audit log", "what did the hooks do?" — or to check, tail, or switch off that logging. Records which hook ran, in which project, under which version, to an append-only log.

arasz Bundle

Use when the whole project — not a diff — is the review target and the result must survive being acted on: "review the entire codebase", "full quality review", "MoE review", "what is wrong with this project", "audit everything before the next release", or a review whose findings will become a plan someone implements. Runs ground-truth baseline, parallel expert lanes, integration, an adversarial pass that tries to falsify the findings, severity calibration against production reality, a reviewed plan, waved implementation in isolated worktrees, and a join review on every merge. Not for judging one diff or PR (that is review-changes plus code-review-checklist), one design document's gates (design-gate-audit), or one question (evidence-first-research).

jordancoin Bundle

Secure iOS apps with Keychain Services, CryptoKit encryption, biometric authentication (Face ID, Touch ID), Secure Enclave key storage, LAContext, App Transport Security (ATS), certificate pinning, data protection classes, and secure coding patterns. Use when implementing app security features, auditing privacy manifests, configuring App Transport Security, securing keychain access, adding biometric authentication, or encrypting sensitive data with CryptoKit.

navikt Skill

Audit whether the current repository and session are ready for effective Grillmester use in OpenCode v1. Use only when the user explicitly asks to check, diagnose, or understand the OpenCode setup; the audit is read-only.

navikt Skill

Self-review the complete scoped diff for correctness, regressions, requirements and repository rules before delivery. Use after implementation or when asked to find problems in changes; use `security-review` for security-specific analysis.

navikt Bundle

Design, implement or diagnose authentication and authorization in a Nav backend. Use for token validation, token exchange, protected endpoints or issuer, audience and 401/403 problems; use `security-review` for a broader security assessment.

navikt Skill

Audit whether the current repository and session are ready for effective Grillmester use in OpenCode v1. Use only when the user explicitly asks to check, diagnose, or understand the OpenCode setup; the audit is read-only.

navikt Skill

Self-review the complete scoped diff for correctness, regressions, requirements and repository rules before delivery. Use after implementation or when asked to find problems in changes; use `security-review` for security-specific analysis.

navikt Bundle

Assess a design or change for security and privacy risks. Use for sensitive data, identity, authorization, trust boundaries, privileged operations or a requested security review; use `auth-overview` to implement an authentication mechanism and `architecture-review` for broader design trade-offs.

navikt Skill

Self-review the complete scoped diff for correctness, regressions, requirements and repository rules before delivery. Use after implementation or when asked to find problems in changes; use `security-review` for security-specific analysis.

navikt Bundle

Evaluate a consequential architecture proposal, its alternatives, migration and reversibility. Use for new services, cross-team boundaries, platform choices or costly migrations; use `improve-codebase-architecture` to discover refactoring candidates in existing code and `security-review` for security analysis.

chorus-aidlc Skill

Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read the integrated code, check cross-task integration / architecture / security / regression / coverage, run tests. Invoke after the last task of an idea-rooted proposal is verified; ends with a VERDICT comment on the Idea.

wadewarren Skill

Google Workspace Admin SDK: Audit logs and usage reports.

pinkpixel-dev Bundle

Implements privileged session monitoring and recording using Privileged Access Management (PAM) solutions, focusing on CyberArk Privileged Session Manager (PSM) and open-source alternatives. Covers session recording configuration, keystroke logging, real-time monitoring, risk-based session analysis, and compliance audit trail generation. Activates for requests involving privileged session recording, PAM session monitoring, CyberArk PSM configuration, administrator activity monitoring, or compliance session auditing.

jh941213 Skill

Diagnose the overall health of the harness (hooks, skills, agents, rules) with scoring. Scope: the global ~/.claude harness (use harness-diagnostics for project-level diagnostics). Triggers on: harness audit, harness diagnosis, config check, harness check. NOT for: writing code, implementation.

mike007jd Bundle

Use when auditing responsiveness, rewards, failures, danger telegraphing, or state-transition feedback in a game.

mike007jd Bundle

Use when converting game audit findings into a structured multi-axis scorecard.

mike007jd Bundle

Use when auditing rollback, compatibility, corruption, or operational risks in a shipped or live-risky game.

mike007jd Bundle

Use when auditing UI sounds, reward/failure cues, danger cues, or audio feedback layering in a game.