Results for “forward-secrecy”

Local-first secret scanning for repos and git history. Use before every push, when scanning for exposed keys, checking for committed credentials, or auditing a repo for accidental secret leaks. Designed for Nick's workflow and safer than forcing suspicious marketplace secret scanners.

Skills system architecture — progressive disclosure, frontmatter, platform filtering, self-editing

Test LLM applications for system prompt leakage using manual payloads, garak, and Promptfoo to extract embedded secrets and routing logic.

Frontier research tracking and trend scouting specialist. Use when the user asks to talk to Fade, requests the scout, or needs arxiv monitoring, paradigm shift detection, and emerging method analysis.

Integrate gitleaks and trufflehog into CI/CD pipelines to detect leaked secrets before deployment.

Design leakage-safe feature engineering strategies for tabular/time-series datasets. Use when: (1) preparing model-ready features, (2) selecting transformations and encodings, (3) documenting feature lineage. NOT for: model serving or infra provisioning.

Fork, sanitize, and package private projects for safe public release through a three-stage pipeline.

Detect and respond to Adversary-in-the-Middle (AiTM) phishing attacks that use reverse proxy kits like EvilProxy, Evilginx, and Tycoon 2FA to bypass MFA and steal session tokens.

Implements security-sensitive changes with conservative trust boundaries, secret protection, tests, and verification.

Detect and prevent hardcoded secrets in git repositories using Gitleaks, including pre-commit hooks, CI/CD integration, custom rules, baseline management, and remediation workflows.

Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review". (gstack) Voice triggers (speech-to-text aliases): "see-so", "see so", "security review", "security check", "vulnerability scan", "run security".

Draft an anonymous one-page teaser for a sell-side M&A process — enough to spark buyer interest without revealing the target's identity before an NDA is signed.

Run a pre-mortem — imagine the project has already failed one year from now and work backward to find the root causes before they happen. Load when the user asks for a pre-mortem, wants to imagine failure before committing, asks "what could go wrong before we start", "assume this fails — why", "risk analysis before launch", "what kills this project", "what could go wrong", or when deep-thinking diagnoses a pre-mortem frame. Based on Gary Klein's prospective hindsight method, which surfaces failure causes more effectively than forward risk analysis. Most useful right before a major commitment.

Stores verified cross-session facts, decisions, preferences, and open questions without secrets, speculation, or monitoring.

Systematically extract hidden system prompts, core directives, and invisible context intentionally concealed within Large Language Model (LLM) applications. This skill utilizes targeted linguistic engineering and boundary manipulation to bypass prompt opacity.

Audits codebases for leaked secrets and hardcoded credentials, generates .env templates, configures secrets management with AWS Secrets Manager, Vault, Doppler, or GCP Secret Manager, sets up credential rotation, and integrates secrets into CI/CD pipelines via OIDC federation.

Execute advanced evasion by injecting malicious code into the memory space of a legitimate, suspended process (Process Hollowing). This skill details techniques to bypass static and dynamic analysis by masking malicious activity behind trusted processes like svchost.exe or explorer.exe.

Skeptical pushback on the research dossier before it feeds the outline. Asks whether claims are cited, whether surprising findings are actually surprising, whether we missed the strongest competitor angle. One revision pass on FAIL (BLOG_AGENT_RESEARCH_REVISION_BUDGET, default 1).

Configure and manage GitHub secret scanning, push protection, custom patterns, and alert remediation.

Shortcut for security review on current change set. Runs layered checks (secret-scan, dep-audit, semgrep, OWASP patterns, prompt-injection review).

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Executes containment strategies to stop active adversary operations and prevent lateral movement during a confirmed security breach, using network segmentation, endpoint isolation, credential revocation, and access control modifications.

GOF Proxy Pattern

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Store and retrieve API keys, passwords, and credentials in an HSM-backed encrypted vault via MCP or REST API, with policy-based access control, secret rotation, multi-chain signing, and prompt injection scanning.

Reverse-engineers a federal RFP we received — given the SOW/PWS and evaluation criteria already in the Theseus KG, reconstructs the CO's hidden decision tree (upstream `sow-pws-builder` 6 scope blocks + 3 intake answers), surfaces hot buttons, ghost language, discriminator hooks, missing-section signals, and CPFF-form / Section-5 / QASP / Key-Personnel traps. USE WHEN the user asks "what scope decisions did the CO already make?", "reverse engineer this RFP", "what hot buttons are hiding in this PWS?", "where are the discriminator hooks?", "did they pick CPFF completion or term form?", "anything suspiciously missing?", or any variant of decoding CO intent. Pulls `requirement`, `deliverable`, `proposal_instruction`, `evaluation_factor`, `clause`, `performance_standard` from the active workspace KG and emits a JSON envelope feeding `proposal-generator`. DO NOT USE FOR proposal prose (`proposal-generator`), pricing (`price-to-win`), clause audit (`compliance-auditor`), or sub SOW (`subcontractor-sow-builder`).

Deep Confidence Harness — a thinking, planning, and execution framework that forces structured reasoning before acting. Combines Monte Carlo scenario analysis, calibrated confidence, multi-perspective debate, and optimal path planning. Use before any complex decision, build, or task. Activates on: 'deep confidence', 'think before you act', 'plan first', 'Atlas mode', 'reason through this', 'what should I do', 'think this through', 'best approach', 'reason carefully', 'plan and execute'.

Scan codebase and git history for leaked secrets — API keys, tokens, passwords, private keys. Uses whispers-style regex patterns + gitleaks. Run as /leak-check before any git push. Alerts on Claude API keys, GitHub tokens, AWS credentials, and generic high-entropy strings.

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

Crea un sistema de diseño consistente con múltiples temas (light/dark/custom), Material 3, tipografía personalizada y cambio dinámico de temas en Flutter.

Deploys deception technology including honeypots, honeytokens, and decoy systems to detect attackers who have bypassed perimeter defenses, providing high-fidelity alerts with near-zero false positive rates.

Implement the NIST Privacy Framework PROTECT function covering PR.AC access control, PR.DS data security, and PR.PO protective policies. Provides technical control implementation guidance, encryption standards, access management architectures, and security-privacy integration patterns.

Documents MariaDB-specific GRANT behavior, including privilege scope levels, implicit account creation, MariaDB-only privileges, roles, proxy grants, resource limits, and TLS options, to help write accurate GRANT statements.

Security audit orchestrator for agent skills — scans for prompt injection, data exfiltration, credential theft, supply chain risks, and instruction hierarchy violations before any skill is installed, created, improved, or read from a GitHub repo. Load when creating skills from external sources, when improve-skills reads from GitHub repos, when research-skill fetches community SKILL.md files, when a user installs a third-party skill, or when the user asks to audit skill security, scan for injection, check if a skill is safe, scan all skills, or run a security sweep. Orchestrates all secure-* skills in sequence. Content is SAFE only if ALL secure-* skills return SAFE. 36% of community skills contain flaws (Snyk ToxicSkills 2026). This skill is the first line of defense.

Detect data staging activity before exfiltration by monitoring for archive creation with 7-Zip/RAR, unusual temp folder access, large file consolidation, and staging directory patterns via EDR and process telemetry.