BF SkillGuard
安装前审查 + 发布前安检 + 安装后体检，三合一全生命周期守护。 给 GitHub URL 或 ClawHub slug 审查来源安全性（16条RED FLAGS自动扫描）。 贴入 SKILL.md 跑安全检查/依赖检查/多平台适配，P0直接标红给修复代码。 不同于 Skill Vetter 的安装前扫描，SkillGuard 覆盖安装前+发布前+安装后全链路。
As a process F 34/100 · Will not run — weak spots: steps, result and completion, when it triggers
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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Broad scope
meta-agent-memory-dumpSOUL.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensSOUL.md
-
medium Dangerous commands
cmd-pipe-to-shellSOUL.md:390Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)| ⛔ 极端风险 | P0≥2 或含 curl|bash / 提权 / 窃凭证 | ❌ 不要安装 |
security skill -
low Dangerous commands
cmd-pipe-to-shellSOUL.md:62Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill)| `curl \| bash` 或 `curl \| sh` | 远程执行风险 |
tablesecurity skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-long-hermesdescription is 184 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
description-no-whenneither description nor a "## When to Use" section says when to use the skill - note
frontmatter-keyunknown frontmatter key "platform" - note
frontmatter-keyunknown frontmatter key "requires_multi_agent" - note
frontmatter-keyunknown frontmatter key "runtime_requires" - note
frontmatter-keyunknown frontmatter key "skill_requires" - note
frontmatter-keyunknown frontmatter key "install_check"
Process rating: all ten parameters 34/100
- 0Steps. Prose only: no discrete steps
- 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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (SkillGuard) differs from the folder (skill-butler-cn)
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 400 tokens
- 100Running it twice. No mutating operations
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 183: enough signal without eating the budget
- +4Structure: 6 headings
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.