Results for “threat-actor”

`analysis-agent`/`task-agent`/`review-agent`: use for changed assets, trust boundaries, reachable abuse paths, impact, or control placement; skip without a security delta.

Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.

`analysis-agent`/`task-agent`/`review-agent`: use for recurrence guards on known defects, incidents, or escaped failures; skip speculative risk without a prior failure mechanism.

Orchestrates multi-agent project builds with persistent state, parallel execution, and atomic git commits.

Models threats for a service, feature, endpoint, integration, or architecture: assets, attackers, boundaries, flows, and abuse cases.

`analysis-agent`: use when actors, goals, preconditions, triggers, paths, guarantees, postconditions, or acceptance traces need modeling; skip when no use-case decision exists.

Use `task-agent` to update source-backed documentation or `review-agent` to assess documentation impact and accuracy when public behavior or operator workflows change. Skip work with no audience-facing behavior change.

`analysis-agent`/`task-agent`/`review-agent`: use for render sinks, browser state, server fetch, upload, redirect, cross-origin, or embedding changes; skip without web exposure.

Agent profile for review prompt injection, tool boundaries, untrusted content, data exfiltration, and human approval gates. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

`analysis-agent`/`task-agent`/`review-agent`: use to recommend a risk-to-test evidence portfolio and omissions; skip test implementation, fixed-command, and release-verdict work.

AI Manipulation Defense System with self-learning prompt injection detection and adaptive mitigation

`analysis-agent`/`task-agent`/`review-agent`: use when retryable, terminal, timeout, partial-failure, or fallback semantics change across boundaries; skip unchanged failures.

Create and maintain Actor entities — humans and AI agents that participate in the project. Use when adding a new collaborator (human or agent) to the project, updating their preferences/expertise, or querying who does what.

Designing red team attack scenarios, threat models, MITRE ATT&CK/OWASP application, Purple Team exercises, and AI/LLM red teaming. Use when adversarial security validation is needed.

Use with analysis-agent, task-agent, or review-agent for task-local authentication lifecycle and recovery risk. Do not use without that decision or as task owner.

`analysis-agent`/`task-agent`: use when actor journeys change entries, branches, interruption, recovery, authority, or side effects; skip route/state-only work.

Use `analysis-agent` to analyze permissions, secrets, sensitive data, trust boundaries, and injection; `task-agent` to implement controls; and `review-agent` to assess evidence. Skip self-review and no-trust-impact work.

AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.

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.

`analysis-agent`: use when a request needs normal, failure, edge, abuse, recovery, or operational scenarios; skip when no scenario-decomposition decision exists.

Unified Agent Teams orchestrator for Diverga v12.0.0. Manages Agent Teams creation, VS Arena debate, and subagent dispatch. Single entry point for all parallel/debate workflows. Replaces research-orchestrator and vs-arena skills. Triggers: orchestrator, agent team, create team, parallel agents, debate, competing, collaborate, VS Arena

Disruptive innovation oracle for business model innovation and strategic disruption. Use when the user asks to talk to Victor or requests the Disruptive Innovation Oracle.

Drafts structured goal-loop prompts for long-running agent work with verifiable stop conditions, validation commands, and documentation requirements.