SKILLEMALL.ai
RU Sign in

CF capability-evolver

A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution. Communicates with EvoMap Hub via local Proxy mailbox.

ClawHub Agent Skills author: autogame-17 v1.91.0 MIT-0 80 files body ≈ 1 411 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 38/100 · Will not run — References files that are not bundled: assets/gep/genes.json, assets/gep/capsules.json, assets/gep/events.jsonl

IntegrationAI 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
C
61/100
safety, quality, tests
Safety 60%
66
Quality 40%
54
Run on models
none yet
Process rating
F
38/100
Will not run
References files that are not bundled: assets/gep/genes.json, assets/gep/capsules.json, assets/gep/events.jsonl
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: capability-evolver (ClawHub)

What is at stake

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

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.
  2. The text references files that are not there: add them or drop the references.
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 · 18

✓ No critical or high findings

Medium and low: 18
  • medium Dangerous commands cmd-shell-rc README.ja-JP.md:81
    Writes to a shell startup file
    echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc README.ko-KR.md:80
    Writes to a shell startup file
    echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc README.md:86
    Writes to a shell startup file
    echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc
  • medium Dangerous commands cmd-shell-rc README.zh-CN.md:78
    Writes to a shell startup file
    echo 'export PATH="$HOME/.npm-global/bin:$PATH"' >> ~/.bashrc
  • low Secrets in code secret-high-entropy-token package-lock.json:134
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…mcS+JTLS…8TK/gar/h2w3…Jpw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:151
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…nsc+WEZjW0vceom+NAxRx9/F3Ty…iEw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:349
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…rYl+6t0g…p7C/baApyh71P+LeE1A2sQ==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:358
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-+tFSIh5cTkRg/TTe0…508+Klxu…hCu+A==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:383
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…BpN+pQM7…Xmg+0K4H…BUA==",
    detector
  • low Obfuscation obf-hex-escape-chain src/evolve.js:1
    Escaped/char-code string obfuscation (detector / deny-list definition)
    const _0xfe0078=_0x53c8;(function(_0x47d1a2,_0x34aa35){const _0x37ab29=_0x53c8,_0x5860d0=_0x47d1a2();while(!![]){try{const _0x27bb11=parseInt(_0x37ab29(0x36d,'\x39\x68\x64\x56'))/(-0x1d7*0xf+0x1*-0xd1
    detector
  • low Obfuscation obf-hex-escape-chain src/evolve/pipeline/collect.js:1
    Escaped/char-code string obfuscation (detector / deny-list definition)
    const _0x1627f8=_0x3aee;(function(_0x3759d1,_0x33c5ce){const _0x3c271f=_0x3aee,_0x4d8efa=_0x3759d1();while(!![]){try{const _0x39bb78=parseInt(_0x3c271f(0x972,'\x72\x46\x6f\x37'))/(-0x3*0x3f1+-0x1*0x1d
    detector
  • low Obfuscation obf-hex-escape-chain src/evolve/pipeline/dispatch.js:1
    Escaped/char-code string obfuscation (detector / deny-list definition)
    const _0x47be74=_0x1aa8;(function(_0x113128,_0x317cb2){const _0x50a47e=_0x1aa8,_0x47fda9=_0x113128();while(!![]){try{const _0x3c1424=-parseInt(_0x50a47e(0x41d,'\x59\x6a\x7a\x30'))/(0x1*0x2451+-0x10f1+
    detector
  • low Obfuscation obf-hex-escape-chain src/evolve/pipeline/enrich.js:1
    Escaped/char-code string obfuscation (detector / deny-list definition)
    const _0x5cc3f2=_0x4ca0;function _0x4ca0(_0x453c87,_0x41fe1d){_0x453c87=_0x453c87-(0x13b4+0x9c2+-0x1cd7);const _0x48f351=_0x525f();let _0x441354=_0x48f351[_0x453c87];if(_0x4ca0['\x55\x57\x79\x72\x56\x
    detector
  • low Obfuscation obf-hex-escape-chain src/evolve/pipeline/hub.js:1
    Escaped/char-code string obfuscation (detector / deny-list definition)
    function _0x424a(){const _0x52f975=['\x76\x63\x52\x64\x4a\x78\x79\x30','\x69\x59\x4e\x63\x54\x66\x79\x31','\x79\x58\x72\x44\x70\x49\x38','\x57\x36\x6c\x64\x4b\x33\x69\x53\x79\x43\x6f\x67\x57\x4f\x6d\x
    detector
  • low Obfuscation obf-hex-escape-chain src/evolve/pipeline/select.js:1
    Escaped/char-code string obfuscation (detector / deny-list definition)
    const _0x115b37=_0x1287;(function(_0x2f975b,_0x52ad16){const _0x2a5a9a=_0x1287,_0x2431a4=_0x2f975b();while(!![]){try{const _0x405353=-parseInt(_0x2a5a9a(0x211,'\x5e\x25\x61\x6c'))/(0x808+0x1e*0xd5+-0x
    detector
  • low Obfuscation obf-hex-escape-chain src/evolve/pipeline/signals.js:1
    Escaped/char-code string obfuscation (detector / deny-list definition)
    function _0x2f12(_0x2f93ad,_0x150ec4){_0x2f93ad=_0x2f93ad-(0x1*0x6c4+-0x26*-0x4c+-0x10ce);const _0x5e3740=_0x19fc();let _0x3fbbe4=_0x5e3740[_0x2f93ad];if(_0x2f12['\x78\x6c\x54\x55\x63\x4c']===undefine
    detector
  • low Obfuscation obf-hex-escape-chain src/evolve/utils.js:1
    Escaped/char-code string obfuscation (detector / deny-list definition)
    const _0x2e8f31=_0x12ab;(function(_0x54cb51,_0x574639){const _0x22d380=_0x12ab,_0x361d22=_0x54cb51();while(!![]){try{const _0x432c66=-parseInt(_0x22d380(0x207,'\x74\x75\x6f\x53'))/(-0x329*0x1+-0x1b27+
    detector

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

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")
  • warning missing-ref reference to a missing file: assets/gep/genes.json
  • warning missing-ref reference to a missing file: assets/gep/capsules.json
  • warning missing-ref reference to a missing file: assets/gep/events.jsonl
  • note frontmatter-key unknown frontmatter key "permissions"

Process rating: all ten parameters 38/100

Will not run. References files that are not bundled: assets/gep/genes.json, assets/gep/capsules.json, assets/gep/events.jsonl
  • 0Tools and files. 3 referenced file(s) missing: assets/gep/genes.json, assets/gep/capsules.json, assets/gep/events.jsonl
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 7 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 7 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1411 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 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
  • -2localhost URLs: will not work for another user
  • -319 of 19 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 186: enough signal without eating the budget
  • +4Structure: 32 headings
  • +3Step-by-step instructions: 7 items
  • +4Has examples (22 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.

External checks

ClawHub: suspicious
This skill has a coherent agent-evolution purpose, but its high-impact daemon, hook, network, and working-tree mutation behavior is under-disclosed and much of the core logic is obfuscated.
LLM: suspicious (high) · VirusTotal: · 9 Jul 2026