secure-agent-orchestration-review SKILL.md skillA
secure-agent-orchestration-review from baphuongna/pi-crew is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add baphuongna/pi-crew/secure-agent-orchestration-review@git:20260911.c97bc57Pins git:20260911.c97bc57 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- baphuongna/pi-crew
- Path
skills/secure-agent-orchestration-review/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260911.c97bc57, committed Sep 11, 2026
- First version recorded
- May 5, 2026
- Size
- 3,559 bytes
- Repository stars
- 57
- License
- MIT
Use when reviewing delegation, skill loading, tool access, worker prompts, artifacts, runtime config, state, ownership, or subprocess execution. When NOT to use: pure code quality issues without security implications (use multi-perspective-review); single-file fixes (use scrutinize).
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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. …
Read the whole file at its exact version.
How to install
mdr add baphuongna/pi-crew/secure-agent-orchestration-review@sha256:24550c8c923d7aceThe line at the top of this page pins the label git:20260911.c97bc57, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_4zzknkzb4lnk6mjf)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between May 5, 2026 and Sep 11, 2026, about one every 32 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260911.c97bc57 latest | 2026-09-11 | c97bc57 | 3,559 B | A | view · diff |
| git:20260603.fa30bc0 | 2026-06-03 | fa30bc0 | 3,414 B | A | view · diff |
| git:20260529.53de3c2 | 2026-05-29 | 53de3c2 | 3,398 B | A | view · diff |
| git:20260528.67ddbec | 2026-05-28 | 67ddbec | 3,372 B | A | view · diff |
| git:20260505.51031a0 | 2026-05-05 | 51031a0 | 2,261 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3559 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
baphuongna/pi-crew · 57 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4zzknkzb4lnk6mjf GET https://markdownregistry.com/api/v1/resolve?ref=baphuongna/pi-crew/secure-agent-orchestration-review GET https://markdownregistry.com/api/v1/blob/24550c8c923d7aced6aeaf3d7fcbad9c5a1d3ad264e334027c119a75a873df14
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.