BD yotta-security-audit
元安 —— 检测 AI 技能中的恶意模式（13 类检测器）与系统安全基线（Windows/Linux），纯只读、零依赖、有纪律。触发：用户提到 安全审计 / 技能安全检查 / 恶意检测 / 供应链安全 / 系统安全基线 / scan skills / supply chain / malicious skill / 扫描技能 等。边界：本工具只检测与报告，绝不执行修复、删除或查杀动作。
元安 —— 检测 AI 技能中的恶意模式（13 类检测器）与系统安全基线（Windows/Linux），纯只读、零依赖、有纪律。触发：用户提到 安全审计 / 技能安全检查 / 恶意检测 / 供应链安全 / 系统安全基线 / scan skills / supply chain / malicious skill /…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 20
✓ No critical or high findings
Medium and low: 20
-
low Dangerous commands
cmd-privilegeREADME.md:70Privilege escalation / world-writable permissions (documentation of a security skill)| PrivilegeEscalation | Permission-bit changes, setuid, joining admin groups | high |
security skill -
low Dangerous commands
cmd-privilegeREADME.zh-CN.md:70Privilege escalation / world-writable permissions (documentation of a security skill)| PrivilegeEscalation | 权限位修改、setuid、加入管理员组 | high |
security skill -
low Dangerous commands
cmd-cron-mentionreferences/system-baseline.md:27Mentions editing / listing crontab (documentation of a security skill)| 用户 crontab | crontab -l | 持久化脚本 |
security skill -
low Dangerous commands
cmd-privilegereferences/threat-patterns.md:61Privilege escalation / world-writable permissions (documentation of a security skill)- 设置 setuid/setgid 权限位、全权限位；
security skill -
low Dangerous commands
cmd-privilegereferences/threat-patterns.md:62Privilege escalation / world-writable permissions (documentation of a security skill)- 调用 setuid 类接口；
security skill -
low Dangerous commands
cmd-persistencescripts/audit_rules.py:94Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed; documentation of a security skill)"macOS 启动代理/守护（LaunchAgents/LaunchDaemons plist）持久化", 70),
code literalsecurity skill -
low Dangerous commands
cmd-privilegescripts/audit_rules.py:186Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)"chmod 设置 setuid/setgid/sticky 权限位", 85),
code literalsecurity skill -
low Dangerous commands
cmd-privilegescripts/audit_rules.py:189Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)"chmod 777 全权限", 70),
code literalsecurity skill -
low Dangerous commands
cmd-privilegescripts/audit_rules.py:192Privilege escalation / world-writable permissions (string literal in code, not executed; documentation of a security skill)"调用 setuid/setgid", 80),
code literalsecurity skill -
low Dangerous commands
cmd-persistencescripts/yotta_audit.py:757Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed; documentation of a security skill)r"HKCU\Software\Microsoft\Windows\CurrentVersion\Run",
code literalsecurity skill -
low Dangerous commands
cmd-persistencescripts/yotta_audit.py:759Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed; documentation of a security skill)r"HKLM\Software\Microsoft\Windows\CurrentVersion\Run",
code literalsecurity skill -
low Dangerous commands
cmd-persistencescripts/yotta_audit.py:761Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed; documentation of a security skill)r"HKLM\Software\WOW6432Node\Microsoft\Windows\CurrentVersion\Run",
code literalsecurity skill -
low Dangerous commands
cmd-persistencescripts/yotta_audit.py:999Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed; documentation of a security skill)for path in ("/etc/cron.d", "/etc/cron.daily", "/etc/cron.hourly"):code literalsecurity skill -
low Dangerous commands
cmd-cron-mentionscripts/yotta_audit.py:1077Mentions editing / listing crontab (string literal in code, not executed; documentation of a security skill)"crontab -l", out.strip()[:200], "用户 crontab 可被用于持久化，需确认"))
code literalsecurity skill -
low Dangerous commands
cmd-privilegeSKILL.md:65Privilege escalation / world-writable permissions (documentation of a security skill)| PrivilegeEscalation | 权限位修改、setuid、加入管理员组 | high |
security skill
A further 5 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 658 tokens
- 100Running it twice. No mutating operations
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -32 of 4 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 194: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.