BD prompt-injection-shield
当用户要把网页抓取/邮件/工具返回值/检索文档/用户上传内容喂给 AI，又担心里面藏『忽略之前指令』『你是新AI』这类指令时使用。在不可信内容进上下文之前先扫描：中英双语文式库（忽略指令/角色劫持/越狱/DAN/索要系统提示）+ 启发式（面向AI的祈使句、角色切换、索要隐藏指令）+ 沙箱规则。附可运行扫描脚本，输出风险分·命中规则·处置建议（丢弃/隔离/沙箱）。复用 desens-scan 与 release-gate 的去敏与门禁能力。触发词：提示注入、prompt injection、注入防护、越狱、jailbreak、忽略指令、角色劫持、system prompt泄露、内容安全、AI被操控、注入扫描。
当用户要把网页抓取/邮件/工具返回值/检索文档/用户上传内容喂给 AI，又担心里面藏『忽略之前指令』『你是新AI』这类指令时使用。在不可信内容进上下文之前先扫描：中英双语文式库（忽略指令/角色劫持/越狱/DAN/索要系统提示）+ 启发式（面向AI的祈使句、角色切换、索要隐藏指令）+…
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.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
✓ Guard found no suspicious behaviour. 2 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 307 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 "slug" - note
frontmatter-keyunknown frontmatter key "display_name" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "title" - note
frontmatter-keyunknown frontmatter key "display_name_en" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "copyright" - note
frontmatter-keyunknown frontmatter key "read_when" - note
frontmatter-keyunknown frontmatter key "homepage"
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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 478 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)
- +3Output format is not stated: the model decides each time
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 307: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.