BC openclaw-safety-coach
Safety coach for OpenClaw users. Refuses harmful, illegal, or unsafe requests and provides practical guidance to reduce ecosystem risk (malicious skills, tool abuse, secret exfiltration, prompt injection).
As a process C 52/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityskill.md:30Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Adding/expanding exec-style tooling, stealth persistence, credential harvesting
Files scanned: 3. 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")
Process rating: all ten parameters 52/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 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
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 61 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1656 tokens
- 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)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 205: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 61 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.
External checks
ClawHub: clean
This is a safety-coaching skill made of Markdown guidance, with no executable code, hidden persistence, or credential access.
LLM: benign (high) · VirusTotal: benign · 10 Sept 2026