SKILLEMALL.ai
GitHub ↗ RU Sign in

AD lygo-pure-data-witness

Teach agents to register pages into the LYGO Pure-Data lattice via the public register portal pack + safety-gated CLI. Archive URLs/files as digests (HTTPS-only, SSRF block, malware/ad heuristics, size cap), pack tiny eggs, rebuild ledger, emit Continuum claims and Star Chart NODE_PDW_* submissions. Use when user asks to witness, archive, pure-data register, PDW, or use the Data Vault register portal. Network only with --i-authorize-fetch; live chart writes need --i-consent. The pure_data_witness.py fetch path and all URL mode also require --i-authorize-fetch. The all chain additionally requires --i-confirm-chain (multi-step persistence warning). HF export pack is local-only and requires --i-consent + --i-authorize-hf-export.

ClawHub Agent Skills author: LYRA Agent - LYGO OS v1.3.0 MIT-0 10 files body ≈ 1 522 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Teach agents to register pages into the LYGO Pure-Data lattice via the public register portal pack + safety-gated CLI.

As a process D 45/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationGitHubAI 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
A
93/100
safety, quality, tests
Safety 60%
93
Quality 40%
92
Run on models
none yet
Process rating
D
45/100
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

    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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Exfiltration intent-browser-credential-store skill-card.md:25
      Accesses a browser credential / cookie store (documentation of a security skill)
      Risk: The skill can archive operator-supplied files or explicitly approved HTTPS URLs, so private files, credentials, cookies, internal URLs, or confidential pages could be captured if the operator po
      security skill
    • low Secrets in code secret-high-entropy-token scripts/pdw_cli.py:94
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "signature": "Δ9Φ963-HAVE…-v1",
      detector
    • low Secrets in code secret-high-entropy-token scripts/pure_data_witness.py:25
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      EGG_SIG = "Delt…-v1"
      quoted

    Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    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
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 4 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
    • 100Steps. 21 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1522 tokens
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

    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
    • +2Single-language instructions
    • +3Description length 735: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 21 items
    • +4Has examples (4 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 4 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.

    External checks

    ClawHub: clean
    The skill is a consent-gated archiving helper that hashes local files or explicitly approved HTTPS URLs and writes local witness artifacts without hidden publishing or persistence.
    LLM: benign (high) · VirusTotal: · 21 Aug 2026