BC agentguard
AgentGuard security engine — intercept dangerous operations, audit all actions, protect sensitive data. All commands/file/network operations go through ag_* tools for rule engine review. AgentGuard 安全引擎 — 拦截危险操作、审计所有行为、保护敏感数据。所有命令/文件/网络操作通过 ag_* 工具经规则引擎审核后执行。
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 7. 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") - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "command-dispatch" - note
frontmatter-keyunknown frontmatter key "command-tool" - note
frontmatter-keyunknown frontmatter key "command-arg-mode"
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (agentguard) differs from the folder (jjy-agentguard)
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 36 steps
- 100Execution cost. Instruction body is 1510 tokens
- 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 12 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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
- +4No input/output examples
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 259: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 36 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.
External checks
ClawHub: suspicious
AgentGuard is purpose-aligned as a security proxy, but it asks users to trust a privileged, long-running daemon and broad command/file/network mediation that cannot be fully reviewed from the provided artifacts.
LLM: suspicious (high) · VirusTotal: · 29 May 2026