BC openclaw-watch
🛡️ AI Agent Immune System — Security scanner + PII sanitizer + intent-action mismatch detector. 285+ patterns, OWASP Agentic AI Top 10. 100% local, zero cloud dependencies.
As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 0
✓ No critical or high findings
Files scanned: 2. 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 59/100
- 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
- 30Running it twice. 3 mutating operations with no state check
- 65Failures and branches. 3 branches
- 100Tools and files. No external tools needed
- 100Steps. 7 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 735 tokens
- 100Progress reporting. Reports progress
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 173: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 7 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.
External checks
ClawHub: suspicious
This skill has a legitimate security-scanning purpose, but it tells agents to automatically run an unpinned npm package in broad situations.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026