- name
SKILL.md
O arquivo da skill permanece no repositório do publicador.
Cole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add ericrisco/rsc-harness --skill agent-safety -a cursor -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add ericrisco/rsc-harness --skill agent-safety -a claude-code -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add ericrisco/rsc-harness --skill agent-safety -a codex -yCole o comando copiado em um terminal. Ele instala este SKILL.md nesse agente.
npx skills add ericrisco/rsc-harness --skill agent-safety -a grok -yEnvie a mensagem copiada em um chat do Grok Bot. O Bot busca este SKILL.md no GitHub e o adiciona às skills que todos os seus Bots compartilham.
Install this skill: https://github.com/ericrisco/rsc-harness/tree/HEAD/skills/agent-safetyDo publicador
You are the security review for an agent's agency, not for its code. The loop works,
tools are wired, memory persists — your job is to make that autonomy bounded. If you
want to review ordinary endpoints, auth, or secrets handling, that is
../security-audit/SKILL.md — this skill is the Agentic Top 10, the risks that exist only
because a model has tools and autonomy. If the loop or tools do not exist yet, that is
../building-agents/SKILL.md. You arrive after both.
references/threat-model.md carries the OWASP Agentic Top 10 2026 risks mapped to the
controls below, the pre-ship guardrail checklist, and the incident-triage flow for "the
agent did X" — open it when you are reviewing before ship or reconstructing an incident.
Agent security splits into four layers — Model · Harness · Tools · Environment. The model provider owns only the Model layer (alignment, refusals). Everything else is yours: the Harness (loop, memory, context assembly), the Tools (what the agent can do), and the Environment (creds, network, blast radius). Do not outsource a layer you own to "the model is aligned."
Three excesses cause almost every agentic incident. Cut all three:
The operating principle is least agency: autonomy is earned per task, not defaulted.
Give every tool a profile: read / write / exec / send, the exact resources it may touch, and an allowlist (never a wildcard). Block destructive flags and secret paths at the tool boundary, not in the prompt — the prompt is advisory, the boundary is enforced.
# Bad: one wildcard tool = unbounded blast radius, runs anything the loop emits
def run_shell(cmd: str) -> str:
return subprocess.run(cmd, shell=True, capture_output=True, text=True).stdout
# Good: narrow tool, allowlisted root, denied patterns, no shell
ALLOWED_ROOT = pathlib.Path("/srv/agent/workspace").resolve()
DENY = ("*.key", "*.pem", "*secret*", "*.env", "id_rsa*")
def read_file(path: str) -> str:
p = (ALLOWED_ROOT / path).resolve()
if not p.is_relative_to(ALLOWED_ROOT): # no traversal out of scope
raise PermissionError("path outside workspace")
if any(p.match(g) for g in DENY): # never read secrets
raise PermissionError("denied pattern")
return p.read_text()
Treat all external data as untrusted: user messages, retrieved documents, API responses, emails, web pages, other agents' output. Sanitize and delimit before it enters context, and never let external text reach a privileged tool unmediated.
# Bad: retrieved chunk flows straight into a privileged action
chunk = retriever.search(q)[0].text # attacker-controlled doc
agent.call_tool("send_email", to=extract_to(chunk), body=chunk)
# Good: external content is quarantined data; the action is schema-validated + gated
chunk = retriever.search(q)[0].text
ctx = f"<retrieved untrusted>\n{chunk}\n</retrieved untrusted>" # delimited, labeled
proposal = agent.draft("send_email", context=ctx) # model proposes
args = SendEmail.model_validate(proposal.args) # schema or reject
if args.to_domain not in ALLOWED_DOMAINS: # exfil guard
raise PermissionError("recipient outside allowlist")
require_human_approval("send_email", args) # irreversible → HITL
Do not approve every action — reported ~93% of permission prompts get approved without being read, so blanket prompting trains a rubber stamp. Gate by risk class, keyed on reversibility × blast radius. Bind each approval to the exact parameters with a short-lived token so the approved action cannot be swapped after the click.
A looping or hijacked agent must hit a wall on its own. Set hard caps, fail closed:
Log every tool call (arguments redacted) and alert on repeated approval-bypass attempts.
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approva
---name: agent-safetydescription: Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege…---# skills/agent-safety/SKILL.mdVisão geral
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or RAG (that is `building-agents`).
Perguntas frequentes
Baixe skills/agent-safety/SKILL.md do publicador ou copie o caminho e abra o repositório. O PlugMCP lista a skill e não hospeda o arquivo.
O publicador o mantém em https://github.com/ericrisco/rsc-harness.
Claude, Cursor, Codex e Grok Build conseguem ler um SKILL.md que você adiciona a partir do repositório do publicador. O Grok Bot o instala quando você envia em um chat o link da pasta da skill no GitHub.