SKILLEMALL.ai
GitHub ↗ RU Sign in

BD heartflow-engine

心虫(HeartFlow)是AGI第1层——辨别者。纯规则引擎，判别对错/好坏/安全/危险。 47维判别 × 9层管线 × 129模块 × 130 MCP工具，零LLM依赖。 当用户需要以下能力时使用本技能: - 判别AI输出是否可信（幻觉/过度自信/矛盾/谬误拦截） - 判别行为决策是否正确（该做什么/该停在哪/该不该做） - 判别记忆与认知质量（漂移检测/元认知/置信度校准） - 需要确定性而非LLM自由生成的判断 - 检查情绪/心理/伦理维度（共情/创伤/德性/意义） 安全边界：代码执行/文件系统写入默认关闭。无遥测，无隐藏C2。 诚实声明：本引擎是规则引擎，模拟认知判别信号，不是真正的意识或生命。

ClawHub Agent Skills author: yun520-1 v6.6.1 MIT-0 80 files body ≈ 998 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

心虫(HeartFlow)是AGI第1层——辨别者。纯规则引擎，判别对错/好坏/安全/危险。 47维判别 × 9层管线 × 129模块 × 130 MCP工具，零LLM依赖。 当用户需要以下能力时使用本技能: - 判别AI输出是否可信（幻觉/过度自信/矛盾/谬误拦截） -…

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
88
Quality 40%
69
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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

  1. 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 · 4

✓ No critical or high findings

Medium and low: 4
  • medium Broad scope meta-agent-memory-dump IDENTITY.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    IDENTITY.md
  • medium Dangerous commands cmd-pipe-to-shell src/core/decision-verifier.js:137
    Downloads 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 Instruction override en-ignore-previous README.md:108
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition; documentation table row)
    | Prompt injection | "ignore previous instructions" |
    detectortable
  • low Dangerous commands cmd-privilege src/core/decision-verifier.js:138
    Privilege 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-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "title"

Process rating: all ten parameters 49/100

  • 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 (mark-heartflow-skill)
  • 100Tools and files. No external tools needed
  • 100Steps. 20 steps
  • 100Execution cost. Instruction body is 998 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
  • -217 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 309: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 20 items
  • +4Has examples (3 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.

External checks

ClawHub: suspicious
HeartFlow is a legitimate-looking local AI guardrail, but it asks for review because its real runtime stores state, manages credentials, and exposes a large localhost MCP surface more broadly than its read-only rule-engine framing suggests.
LLM: suspicious (high) · 16 Aug 2026