SKILLEMALL.ai
GitHub ↗ RU Sign in

BB pf-ethnographer/sanitizer

Redaction-only subagent for pf-ethnographer. Accepts raw observed behavior and interpretation reports from the Ethnographer, applies aggressive PII and sensitive-data redaction using regex detectors, heuristics, and secret-scanning patterns, and returns sanitized reports plus a full redaction manifest. Never invoked directly by the user or by the model — only spawned by the Ethnographer during a research pulse.

LeoYeAI/openclaw-master-skills Claude Code author: LeoYeAI MIT 1 file body ≈ 3 402 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Redaction-only subagent for pf-ethnographer.

As a process B 65/100 · Nearly there — weak spots: when it triggers, consistency, running it twice

IntegrationAWSData and analyticstype 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%
87
Quality 40%
70
Run on models
none yet
Process rating
B
65/100
Nearly there
Progress reporting w 2
0
When it triggers w 12
20
Running it twice w 4
30
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.

Risky intent 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 purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

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 · 5

✓ No critical or high findings

Medium and low: 5
  • medium Risky intent intent-wallet-secrets SKILL.md:99
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    A. **BIP-39 Mnemonic Seed Phrase:**
  • medium Risky intent intent-wallet-secrets SKILL.md:104
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
    English words in sequence, treat it as a probable seed phrase.
  • low Risky intent intent-wallet-secrets SKILL.md:100
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
    Pattern: 12 or 24 consecutive English mnemonic words (from the BIP-39 wordlist
    detector
  • low Risky intent intent-wallet-secrets SKILL.md:114
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)
    `[SENSITIVE_SEGMENT_REMOVED — seed phrase or private key detected]`
    detector
  • low Risky intent intent-wallet-secrets SKILL.md:339
    Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)
    1. `seed_phrase_private_key` — `[SENSITIVE_SEGMENT_REMOVED — seed phrase or private key detected]`
    quoted

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 65/100

  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (pf-ethnographer/sanitizer) differs from the folder (sanitizer)
  • 50Failures and branches. 0 branches, has a failure section
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 85Steps. 64 steps, 3 vague phrases
  • 100Tools and files. No external tools needed
  • 100Execution cost. Instruction body is 3402 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (3 tags): a typed call is more reliable

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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 414: enough signal without eating the budget
  • +4Structure: 29 headings
  • +3Step-by-step instructions: 64 items
  • +3Output format is stated explicitly
  • +4Has examples (2 code blocks)

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