secure-agent-orchestration-review

secure-agent-orchestration-review is a skill for Claude Code, Codex from baphuongna/pi-crew. It costs 34 tokens per session (680 once invoked), scanned A, original, MIT.

A security review guide for systems where coding agents delegate work to other workers or use external skills and tools.

In plain words
What is it for?
Use it to review worker prompts, delegated tasks, tool permissions, runtime settings, files and artifacts, subprocesses, and ownership boundaries.
Why use it?
It helps identify unsafe defaults, overly broad access, path escapes, prompt injection, secret leaks, and risky commands before they cause harm.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review worker prompts, delegated tasks, tool permissions, runtime settings, files and artifacts, subprocesses, and ownership boundaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/baphuongna/pi-crew/secure-agent-orchestration-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add baphuongna/pi-crew --skill secure-agent-orchestration-review
Clone the repo
git clone --depth 1 https://github.com/baphuongna/pi-crew

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for secure-agent-orchestration-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/baphuongna/pi-crew/secure-agent-orchestration-review/github.svg)](https://agentmods.dev/skills/baphuongna/pi-crew/secure-agent-orchestration-review)
Your own site
<a href="https://agentmods.dev/skills/baphuongna/pi-crew/secure-agent-orchestration-review"><img src="https://agentmods.dev/badge/skills/baphuongna/pi-crew/secure-agent-orchestration-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for secure-agent-orchestration-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/baphuongna/pi-crew/secure-agent-orchestration-review"><img src="https://agentmods.dev/badge/skills/baphuongna/pi-crew/secure-agent-orchestration-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 71
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.00680
Opus 5 $0.00017 $0.00340
Sonnet 5 $0.00007 $0.00136
Haiku 4.5 $0.00003 $0.00068

Measured 11d ago against content hash fd2cc38fc773, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

secure-agent-orchestration-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/secure-agent-orchestration-review/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

secure-agent-orchestration-review

Core principle: every delegated worker crosses trust boundaries. Safe orchestration requires contained paths, explicit ownership, scoped tools, non-invasive defaults, and prompt-injection resistance.

Distilled from detailed reads of security notice, insecure-defaults, sharp-edges, differential-review, guardrail, and skill quality patterns.

Trust Boundaries

Review:

  • parent session ↔ child Pi worker;
  • user prompt ↔ generated task packet;
  • project skills ↔ package skills;
  • global config ↔ project config;
  • artifacts/logs ↔ future prompts/UI;
  • mailbox/respond/steer/cancel ↔ session ownership;
  • external skills/docs ↔ prompt injection/tool poisoning;
  • runtime env/CLI args ↔ provider/model behavior.

Must-Check Findings

  • Unsafe defaults: scaffold mode unexpectedly enabled, dangerous limits, missing depth guards, overbroad tools.
  • Path containment: cwd override escape, symlink traversal, unsafe skill names, absolute path leakage.
  • Prompt injection: untrusted output treated as instruction, skill metadata overtrusted, missing precedence text.
  • Secrets: env/config/log/artifact/diagnostic leakage.
  • Destructive commands: delete/prune/reset/force push without explicit confirmation.
  • Ownership races: authorization checked outside lock, stale task/manifest written after re-read.
  • Supply chain: external skill content imported without review, unknown tool requirements, hidden commands.

Secure Defaults for pi-crew

  • Real execution should be explicit and disable-able, but generated config must not accidentally block normal workflows.
  • Project overrides should be contained to the project root.
  • Missing/invalid config should fall back safely.
  • Skills should be loaded by safe name and source-labeled without absolute path disclosure.
  • Worker prompts should state instruction precedence and treat artifacts as data.

Enforcement — Secure Agent Orchestration Review Gate

Before reporting security findings, verify:

  • All trust boundaries examined (parent↔child, user↔task packet, project↔package skills, etc.)
  • Must-check findings covered: unsafe defaults, path containment, prompt injection, secrets, destructive commands, ownership races, supply chain
  • Finding format complete: severity, path/symbol, scenario, fix, verification
  • Must-fix security issues separated from hardening suggestions
  • Verification commands provided for each finding

Read the full file on GitHub · 74 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 74 lines · 34 tokens per session scan A fd2cc38fc773

Subscribe to this mod's changes

secure-agent-orchestration-review is a skill published in the GitHub repository baphuongna/pi-crew (52 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 680 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens