CD vaikora-security
Route OpenClaw LLM calls through Vaikora for real-time AI agent security monitoring. Every action your agent takes gets scored for risk, anomaly-flagged, and pushed as a security signal to SentinelOne, CrowdStrike, or AWS Security Hub, without changing how your agent works.
Route OpenClaw LLM calls through Vaikora for real-time AI agent security monitoring.
As a process D 46/100 · Unfinished process — 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.
- 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 Exfiltration
net-credential-useSKILL.md:119Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -H "x-api-key: ${VAIKORA_API_KEY}" \security skill
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 46/100
- 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. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (vaikora-security) differs from the folder (vaikora)
- 85Steps. 25 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 1571 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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 274: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.