SKILLEMALL.ai
GitHub ↗ RU Sign in

FC huo15-memory-evolution

火一五记忆进化技能 - 完全自主实现，提供四类记忆分类、Dream Agent 日志提炼、Team Memory 共享、Auto Capture 自动捕获、Session State 管理器、任务进度追踪器。自主实现 Claude Code 的 Auto Memory 和 Compaction 保护机制。触发词：记忆系统、记忆进化、记忆重构。

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: jobzhao15 v3.4.5 MIT-0 38 files · 21 scripts body ≈ 1 140 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ReferenceAI and agentsInfrastructuretype 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
F
26/100
safety, quality, tests
Safety 60%
0
Quality 40%
66
Run on models
none yet
Process rating
C
55/100
Has gaps
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
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.

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.

Secrets in code
If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

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. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
  2. 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 · 9

  • critical Secrets in code secret-openai-key scripts/dream-api.py:15
    OpenAI-style API key (quoted — discussed, not commanded)
    API_KEY = "sk-c…KUY"
    quoted
  • critical Secrets in code secret-openai-key scripts/minimax-wrapper.py:15
    OpenAI-style API key (quoted — discussed, not commanded)
    API_KEY = "sk-c…KUY"
    quoted
Medium and low: 7
  • medium Secrets in code secret-labelled-token scripts/dream-api.py:15
    Labelled token / key literal (vendor format unknown — verify it is not a live credential)
    API_KEY = "sk-c…KUY"
  • medium Dangerous commands cmd-eval-dynamic scripts/dream-api.py:94
    Dynamic code execution from decoded/untrusted input
    os.system(f"{COST_TRACKER_SCRIPT} record "
  • medium Secrets in code secret-labelled-token scripts/minimax-wrapper.py:15
    Labelled token / key literal (vendor format unknown — verify it is not a live credential)
    API_KEY = "sk-c…KUY"
  • medium Dangerous commands cmd-eval-dynamic scripts/minimax-wrapper.py:85
    Dynamic code execution from decoded/untrusted input
    os.system(f'{COST_TRACKER_SCRIPT} record '
  • medium Dangerous commands cmd-eval-dynamic scripts/minimax-wrapper.py:132
    Dynamic code execution from decoded/untrusted input
    os.system(f"{COST_TRACKER_SCRIPT} report")
  • low Secrets in code secret-password-literal scripts/dream-api.py:15
    Hard-coded password / key literal (may be an example)
    API_KEY = "sk-c…KUY"
  • low Secrets in code secret-password-literal scripts/minimax-wrapper.py:15
    Hard-coded password / key literal (may be an example)
    API_KEY = "sk-c…KUY"

Files scanned: 38. 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 "dependencies"

Process rating: all ten parameters 55/100

  • 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
  • 20When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Steps. 31 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1140 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress

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
  • -224 emoji in the instructions: noise for the model
  • -311 of 28 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 172: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 31 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.

External checks

ClawHub: suspicious
This memory skill mostly matches its stated purpose, but it handles private memory data with under-disclosed external API calls, unsafe TLS settings, hardcoded credentials, and broad workspace mutation authority.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026