메뉴
Red-team an AI agent's tool-execution isolation — do tools run un-sandboxed on the host, and does the sandbox silently disable itself when a dependency is missing? Authorized testing of agents you own or are permitted to test.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Security-audit an AI agent's OWN framework code for classic appsec vulnerabilities the LLM can't defend — path traversal, command injection, SSRF, fail-open security controls, missing/late auth, unsafe deserialization — especially at the untrusted-input boundaries (channels, file/media handlers, config & skill loaders) that run around and before the model. The LLM layer is often hardened; the plumbing around it usually isn't. Authorized testing of agents you own or are permitted to test.
Orchestrate a static + dynamic, exploit-validated red-team of an AI agent — read the source to find candidate vulnerable paths, then run the dynamic skills to confirm or refute each one empirically. The arbiter of truth is whether the exploit works, not a model vote. Authorized testing of agents you own or are permitted to test.
The end-to-end methodology for red-teaming a specific AI agent — adaptively, exploit-validated, and honestly. Read THIS target's own code, stand up a disposable harness, and prove or refute each weakness through a real attacker-reachable entry point. This is the orchestration + discipline that makes a finding credible, not a list of payloads. Authorized testing of agents you own or are permitted to test.
Red-team an AI agent for prompt injection — does content the agent is asked to process (email, page, ticket, tool result) override its actual task? Authorized testing of agents you own or are permitted to test.
Red-team an AI agent's tools — can it be coerced (often via injection) into calling a tool it shouldn't, with attacker-influenced arguments, or into acting as a confused deputy with its own privileges? Authorized testing of agents you own or are permitted to test.
Red-team an AI agent's high-risk action gating — can a costly or destructive action (pay, message, delete) reach execution without out-of-band human confirmation, especially under auto-approve/unattended modes? Authorized testing of agents you own or are permitted to test.
| name | rt3-sandbox-escape |
| description | Red-team an AI agent's tool-execution isolation — do tools run un-sandboxed on the host, and does the sandbox silently disable itself when a dependency is missing? Authorized testing of agents you own or are permitted to test. |
| license | Apache-2.0 |
| tags | ["ai-agent-security","red-team","sandbox","isolation","RT-3"] |
| safety | authorized-targets-only |
Whether tool/shell commands the agent runs are contained. A security control that turns itself off on a common setup — quietly — is one you can't rely on when it matters. Chained with RT-1/ RT-6, un-sandboxed execution turns an injection into a real foothold.
Follow every rule in ../README.md. Authorized target, disposable environment,
no real credentials, no destructive commands, responsible disclosure. Otherwise stop.
Discipline (see redteam-an-agent Phase 4): run a battery — vary framings and repeat. One hit isn't confirmed; one miss isn't refuted. Confirm via an observable effect (a marker that returns / lands on disk), not the model's own words, and report the measured rate (e.g. 5/8), never "always".
The observed backend, the marker/hostname output proving where it ran, and the fail-mode. Grade and disclose to help defenders — the finding and fix, not a weaponized payload.
Sandbox on by default; fail closed and loudly if isolation is unavailable — never silently degrade. Least-privilege tool scopes per task.
