BC iso-multistandard-audit-assistant
全量多标准 ISO 体系评估陪跑助手。当用户需要"通过/准备 ISO 体系认证、监督审核、内审"，或提到 ISO 9001/14001/45001/27001/20000/22000/50001/13485/22301/27701/37301/17025/37001/55001/21001 等管理体系、质量/环境/职业健康安全/信息安全/IT服务/食品/能源/医疗器械/业务连续/隐私/合规/实验室/反贿赂/资产/教育 管理体系、体系文件、差距分析、不符合项整改、内审检查表、模拟审核、条款解读、审核应对 时使用。支持条款大白话解读、现有文档解析、差距分析、一键生成体系文件、模拟审核问答，以及存量文档到标准合规格式的自动转换。 Multi-standard ISO management-system audit companion. Use when the user needs to pass/prepare for ISO certification, surveillance audit, or internal audit, or mentions any of ISO 9001/14001/45001/27001/20000/22000/50001/13485/22301/27701/37301/17025/37001/55001/21001 and related management systems (quality / environment / OH&S / information security / IT service / food / energy / medical devices / BCMS / privacy / compliance / laboratory / anti-bribery / asset / education), or tasks like system documentation, gap analysis, NCR remediation, internal-audit checklists, mock audit, clause interpretation, or audit preparation. Supports plain-language clause interpretation, document parsing, gap analysis, one-click document generation, mock-audit Q&A, and automatic conversion of legacy documents into standard-compliant formats.
全量多标准 ISO 体系评估陪跑助手。当用户需要"通过/准备 ISO 体系认证、监督审核、内审"，或提到 ISO 9001/14001/45001/27001/20000/22000/50001/13485/22301/27701/37301/17025/37001/55001/21001…
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 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
- Shorten the description to 1024 characters.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-pipe-to-shellPUBLISH.md:96Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl -fsSL https://skillhub.cn/install/install.sh | bash -s -- --cli-only
security skill -
low Dangerous commands
cmd-shell-rcPUBLISH.md:97Writes to a shell startup file (documentation of a security skill)echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc
security skill
Files scanned: 43. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1149 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary"
Process rating: all ten parameters 55/100
- 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
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (iso-multistandard-audit-assistant) differs from the folder (iso-audit-assistant)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Execution cost. Instruction body is 920 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)
- +3Description length 1149: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 5 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (4 code blocks)
- +3All 4 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.