Claude Code, Skill
MyR2D2
MyR2D2 — 你的隨行 astromech droid：session 收工落地(save-all)、跨 session 交接與即時門鈴(dropoff/pickup)、工作日誌與日結週結(mission-log/daily-debrief/weekly-debrief)、開工簡報(new-mission)、收尾自檢(damage-report)、系統自檢(systems-check)、跨模型二審(ai-review)、帶引用即時查證(ai-search)、多代理節流(token-optimizer)、航班上行事曆(flight-to-calend
Compatibility: Not stated.
Grade D
Two or more Medium findings, or a High. Only try it in a sandbox.
Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.
INSTALL_REMOTE_SCRIPT SECRETS_PATH_CREDENTIAL
Why this grade
- INSTALL_REMOTE_SCRIPT High
Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).
skills/ai-review/scripts/ai-review.sh, line 199
curl -fsSL https://chatgpt.com/codex/install.sh | sh - SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
skills/systems-check/scripts/selfcheck_scan.py, line 300
if rp == c / ".credentials.json":
Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.
If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.
Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.
What was checked
Plain notes from the hygiene checks.
Permissions
Concern
can delete files.
PERMISSION_DELETE_FILES
skills/systems-check/scripts/selfcheck_scan.py, line 1939
r = subprocess.run(["launchctl", "print", "gui/%d/%s" % (uid, label)],
skills/systems-check/scripts/selfcheck_scan.py, line 2374
r = subprocess.run(["git", "-C", str(root), "rev-parse", "--show-toplevel"],
skills/systems-check/scripts/selfcheck_scan.py, line 2386
r2 = subprocess.run(["git", "-C", str(top), "ls-files", "-z"],
Show more
skills/systems-check/scripts/selfcheck_scan.py, line 3354
subprocess.run(["git", "init", "-q", str(repoA)], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, timeout=30)
skills/systems-check/scripts/selfcheck_scan.py, line 3355
subprocess.run(["git", "-C", str(repoA), "add", "-A"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, timeout=30)
skills/systems-check/scripts/selfcheck_scan.py, line 3922
shutil.rmtree(str(base), ignore_errors=True) # 還原 fixture，別影響其他案
Install and update
Serious
install fetches a script from the network.
INSTALL_REMOTE_SCRIPT
docs/AI_REVIEW_SOURCES.md, line 27
| 官方安裝腳本 | `curl -fsSL https://chatgpt.com/codex/install.sh \| sh` | 官方 CLI 頁原文（`learn.chatgpt.com/docs/codex/cli`，2026-08-20） |
skills/ai-review/scripts/ai-review.sh, line 199
curl -fsSL https://chatgpt.com/codex/install.sh | sh
skills/ai-search/scripts/ai-search.sh, line 173
curl -fsSL https://chatgpt.com/codex/install.sh | sh
Network
Pass
No network call found.
Secrets
Concern
reads a credential or environment file.
SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
skills/systems-check/scripts/selfcheck_scan.py, line 300
if rp == c / ".credentials.json":
skills/systems-check/scripts/selfcheck_scan.py, line 331
if rp == scope.home / ".claude" / ".credentials.json":
skills/systems-check/scripts/selfcheck_scan.py, line 437
ok = in_scope(scope, rp) or _under(rp, scope.home / ".config") or rp == scope.home / ".claude" / ".credentials.json"
Show more
skills/systems-check/scripts/selfcheck_scan.py, line 1741
"build.sh", "index.js", "index.html", ".env", "notes.md", "HANDOFF.md",
skills/systems-check/scripts/selfcheck_scan.py, line 2342
yaml|yml|toml)$|\.(pem|key|p12|token)$|^\.env(\.|$)|^token$|^credentials?$", re.I)
skills/systems-check/scripts/selfcheck_scan.py, line 2347
"""只認憑證檔型（token.json／.env／*.pem…），不再用「檔名含 token」一竿子打翻 .py／.sh／.md／.plist。"""
skills/ai-review/SKILL.md, line 131
別讓不可信的來源（外部 `.env`、CI 變數）決定它的值；
skills/ai-search/SKILL.md, line 126
別讓不可信的來源（外部 `.env`、CI 變數）決定它的值；
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Pass
No encoded or minified payload found.
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.
Note
Hygiene check of commit 32bef4ecbedf. can delete files. install fetches a script from the network. reads a credential or environment file.
Date and source
Date checked:
github.com
Commit graded: 32bef4ecbedf2f50b15abd9e1dbd3bacd5efa417
This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.