FD yotta-memory
元忆 —— 有权限边界的文件式智能体记忆。文件式、零依赖、可 diff/可回滚：让任何 AI 智能体活过会话，开工 recall 恢复上下文、重要信息 remember 落盘、收工归档。类型体系 FACT（公共共享）/ PREF / BOUND / COMMIT（私密隔离）。触发：记住、别忘了、记一笔、记忆、remember、recall、跨会话、上次说到、续测、交接、归档、记忆盘、共享记忆、局域网记忆、画像、开工上下文、记忆守则、profile、context、越用越懂、语义检索、反馈、维护、蒸馏、feedback、maintain、distill、explain、自我学习、自我进化、自我提升、查看平台分页、recall 候选预过滤、任务相关记忆、--focus、--embedding、压缩遗忘、consolidate、周期摘要、自动合并、分类型衰减、回滚
Not recommendedcritical or high security findings · low grade F
元忆 —— 有权限边界的文件式智能体记忆。文件式、零依赖、可 diff/可回滚：让任何 AI 智能体活过会话，开工 recall 恢复上下文、重要信息 remember 落盘、收工归档。类型体系 FACT（公共共享）/ PREF / BOUND /…
As a process D 42/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
Dangerous commands
If you install
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.
For the author
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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 · 13
-
high Dangerous commands
cmd-persistenceCHANGELOG.md:100Persistence mechanism (cron / launchd / scheduled task / autorun registry)- **v0.6.4**：lan enable Linux 开机自启（systemd 用户单元 / 用户 crontab @reboot 降级）。
-
high Dangerous commands
cmd-persistenceREADME.md:256Persistence mechanism (cron / launchd / scheduled task / autorun registry)| `yotta-memory lan enable [--onstart] / disable / status` | Autostart management (Windows: scheduled task, default ONLOGON, --onstart needs admin, non-admin auto-degrades to user-level Startup; Linux
-
high Dangerous commands
cmd-persistenceREADME.zh-CN.md:64Persistence mechanism (cron / launchd / scheduled task / autorun registry)| **局域网共享与自启** | 每智能体独立 token（Bearer + X-Agent-Id）鉴权、可吊销；`lan enable` 注册开机自启（Windows：优先计划任务，非管理员自动降级用户级 Startup 静默自启；Linux：systemd 用户单元，不可用时自动降级用户 crontab @reboot）；MCP 工具集与 CLI 一致（8 个工具），管理动作不远程暴露 |
-
high Dangerous commands
cmd-persistenceREADME.zh-CN.md:147Persistence mechanism (cron / launchd / scheduled task / autorun registry)- **开机自启**：`lan enable` 注册开机自启——Windows 优先计划任务（默认登录自启，`--onstart` 开机即启需管理员），非管理员自动降级为**用户级 Startup 静默自启**（免管理员，启动脚本内联启动命令、被清理也会在开机时自动重建，v0.6.3 起不再弹 80070002）；Linux 优先 **systemd 用户单元**（`systemctl --use
-
high Dangerous commands
cmd-persistenceREADME.zh-CN.md:298Persistence mechanism (cron / launchd / scheduled task / autorun registry)| `yotta-memory lan enable [--onstart] / disable / status` | 开机自启管理（Windows：计划任务，默认 ONLOGON、--onstart 开机即启需管理员，非管理员自动降级用户级 Startup 静默自启；Linux：systemd 用户单元，不可用时自动降级用户 crontab @reboot）|
-
high Dangerous commands
cmd-persistenceSKILL.md:177Persistence mechanism (cron / launchd / scheduled task / autorun registry)| `yotta-memory lan enable [--onstart] / disable / status` | 开机自启管理（Windows：计划任务，默认 ONLOGON、--onstart 开机即启需管理员，非管理员自动降级用户级 Startup 静默自启，v0.6.3 起 VBS 自愈不弹 80070002；Linux：systemd 用户单元，不可用时自动降级用户 crontab
-
high Dangerous commands
cmd-persistenceUSER_GUIDE.md:240Persistence mechanism (cron / launchd / scheduled task / autorun registry)# systemd 不可用时自动降级用户 crontab @reboot（开机自启，免管理员）
-
high Dangerous commands
cmd-persistenceUSER_GUIDE.md:357Persistence mechanism (cron / launchd / scheduled task / autorun registry)| `yotta-memory lan enable [--onstart] / disable / status` | 开机自启管理（Windows：计划任务/用户级 Startup 静默自启；Linux：systemd 用户单元/用户 crontab @reboot）|
Medium and low: 5
-
medium Dangerous commands
cmd-persistencebin/yotta-memory.js:11Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)// v0.6.4 新增：lan 命令扩展 Linux——systemd 用户单元（systemctl --user enable/start，登录自启；--onstart 附加 loginctl enable-linger 开机即启）/ systemd 不可用时自动降级用户 crontab @reboot；lanPlatform 测试钩子（YOTTA_LAN_PLATFORM）
comment -
medium Dangerous commands
cmd-persistencebin/yotta-memory.js:3130Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)// @reboot when no systemd user session is available.
comment -
medium Dangerous commands
cmd-persistencebin/yotta-memory.js:3260Persistence mechanism (cron / launchd / scheduled task / autorun registry) (code comment)// ---- lan Linux (systemd user unit / user crontab @reboot) ----
comment -
medium Dangerous commands
cmd-persistencebin/yotta-memory.js:3294Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)const parts = ['@reboot', shQuote(process.execPath), shQuote(__filename)].concat(lanServeArgs(opts));
code literal -
medium Dangerous commands
cmd-persistencebin/yotta-memory.js:3385Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)console.log('自动改用用户 crontab @reboot 自启...');code literal
Files scanned: 14. 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 42/100
- 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
- 30Running it twice. 13 mutating operations with no state check
- 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
- 70Execution cost. Instruction body is 4514 tokens
- 100Steps. 117 steps
- 100Consistency. Name and required fields are in place
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (34 tags): a typed call is more reliable
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
- -213 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 384: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 117 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.
External checks
ClawHub: suspicious
This appears to be a real memory tool, but it gives agents broad persistent and remote access to private memories and has verified owner-isolation gaps.
LLM: suspicious (high) · 6 Sept 2026