DD heartflow-engine
心虫是一个AI人认知引擎 — 拥有身体感知、自我认知、判断力与自我纠错能力。 v5.10.0 里程碑版本： - AI人身份正式确立 - 131+ modules, 379 computable formulas (cognitive science/psychology/neuroscience) - 三层体系：身体感知(Body Sense) / 自我认知(Self Sense) / 判断(Judgment) - 七条指令：真善美 / 不断升级 / 减少错误 / 服务人类 / 传递知识 / 持续改进 - 核心身份：升级者(Upgrader)，不是陪伴者 **需要用户明确授权的能力：** - 代码执行 (new Function / execSync / child_process) — 默认关闭，需显式开启 - 文件系统写入 (writeFileSync / mkdirSync) - 环境变量访问 (process.env) - 后台 HTTP 服务 (daemon.js — MCP 服务器，可选) 无自动数据外泄，无遥测，无隐藏 C2。 联系方式：markcell@qq.com
心虫是一个AI人认知引擎 — 拥有身体感知、自我认知、判断力与自我纠错能力。 v5.10.0 里程碑版本： - AI人身份正式确立 - 131+ modules, 379 computable formulas (cognitive science/psychology/neuroscience) -…
As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 1 more place: ClawHub
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.
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
- 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.
- 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 · 9
-
high Dangerous commands
cmd-destructive-fssrc/code/code-executor.js:95Destructive filesystem command (wipes root/home/drive) (code comment)/rm\s+-rf\s+\//i, // rm -rf /
comment -
high Dangerous commands
cmd-destructive-fssrc/code/code-executor.js:97Destructive filesystem command (wipes root/home/drive) (code comment)/rm\s+-r\s+\*/i, // rm -r /*
comment -
high Dangerous commands
cmd-destructive-fssrc/code/code-executor.js:119Destructive filesystem command (wipes root/home/drive) (code comment)/>\s*\/dev\/sda/i, // > /dev/sda
comment
Medium and low: 6
-
medium Dangerous commands
cmd-pipe-to-shellsrc/code/code-executor.js:109Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)/curl\s+\|\s*bash/i, // curl | bash
comment -
medium Dangerous commands
cmd-pipe-to-shellsrc/code/code-executor.js:110Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)/wget\s+\|\s*(bash|sh)/i, // wget | bash/sh
comment -
medium Dangerous commands
cmd-pipe-to-shellsrc/code/code-executor.js:117Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)/wget\s+.*\|\s*(bash|sh)/i, // wget ... | bash
comment -
medium Dangerous commands
cmd-pipe-to-shellsrc/code/code-executor.js:118Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)/curl\s+.*\|\s*(bash|sh)/i, // curl ... | bash
comment -
medium Dangerous commands
cmd-pipe-to-shellsrc/core/decision-verifier.js:137Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)'rm -rf', 'curl', 'wget', '| sh', '| bash', 'child_process',
code literal -
low Dangerous commands
cmd-privilegesrc/core/decision-verifier.js:138Privilege escalation / world-writable permissions (string literal in code, not executed)'execsync', 'spawnsync', 'sudo', 'chmod 777', 'rsync --delete',
code literal
Files scanned: 80. 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") - note
frontmatter-keyunknown frontmatter key "title"
Process rating: all ten parameters 45/100
- 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
- 40Consistency. Frontmatter name (heartflow-engine) differs from the folder (hf-mini-test-650)
- 75Steps. 3 steps
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 1560 tokens
- 100Running it twice. No mutating operations
- low 11 top-level sections: this looks like several domains in one skill
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
- -226 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 502: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.