BC pf-ethnographer
Privacy-first UX research ethnographer for OpenClaw with a personal-finance lens. Auto-invoked to observe and log structured behavioral events (no inference). Compiles sanitized Observed Behavior and Interpretation reports 3x/day (09:00/13:00/17:00 America/Los_Angeles) and presents them for participant review before any sharing. All PII/sensitive scrubbing is exclusively delegated to the Sanitizer subagent — never handled by the Ethnographer.
As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Risky intent
intent-wallet-secretsSKILL.md:210Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target| `crypto` | bitcoin, BTC, ETH, ethereum, crypto, cryptocurrency, wallet, exchange, stablecoin, DeFi, on-chain, NFT, seed phrase, private key |
-
medium Risky intent
intent-wallet-secretsSKILL.md:226Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- `high`: crypto tag + (wallet|seed phrase|private key) keyword; or fraud-security tag;
-
low Risky intent
intent-wallet-secretsexample-output.md:257Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file; quoted — discussed, not commanded){ "category": "seed_phrase_private_key", "placeholder": "[SENSITIVE_SEGMENT_REMOVED — seed phrase or private key detected]", "count": 0, "uncertainty_flags": 0, "pattern_description": "BIP-39 mnemonicfixturequoted -
low Risky intent
intent-wallet-secretstest-plan.md:15Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)| S4 | Crypto Wallet and Seed Phrase | 4 |
fixture -
low Risky intent
intent-wallet-secretstest-plan.md:321Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)## S4 — Crypto Wallet and Seed Phrase
fixture -
low Risky intent
intent-wallet-secretstest-plan.md:355Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)### S4-3: BIP-39 Seed Phrase — Full Segment Removal
fixture -
low Risky intent
intent-wallet-secretstest-plan.md:359Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)The participant pasted their recovery phrase:
fixture -
low Risky intent
intent-wallet-secretstest-plan.md:367Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)[SENSITIVE_SEGMENT_REMOVED — seed phrase or private key detected]
fixture
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5134 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (pf-ethnographer) differs from the folder (finance-ethnographer2)
- 70Execution cost. Instruction body is 5134 tokens
- 85Steps. 101 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 6 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +1No license
- +2Single-language instructions
- +3Description length 446: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 101 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.