BD db-security
数据库安全审计，支持SQL注入检测、敏感数据扫描、权限审计、登录安全监控、审计日志分析、密码策略检查、配置安全审计。 使用场景： - 用户说"安全检查" -> 执行 audit - 用户说"检测注入" -> 执行 sql-injection - 用户说"扫描敏感数据" -> 执行 sensitive-data - 用户说"安全评分" -> 执行 score - 用户说"检查权限" -> 执行 permissions - 用户说"登录安全" -> 执行 login-security - 用户说"审计日志" -> 执行 audit-log - 用户说"高危操作" -> 执行 high-risk - 用户说"密码策略" -> 执行 password-policy - 用户说"弱密码" -> 执行 weak-passwords - 用户说"配置安全" -> 执行 config 用法： - dbskiter --output-mode=ai --database=<name> security audit - dbskiter --output-mode=ai --database=<name> security sql-injection "<SQL>" - dbskiter --output-mode=ai --database=<name> security sensitive-data - dbskiter --output-mode=ai --database=<name> security score - dbskiter --output-mode=ai --database=<name> security permissions - dbskiter --output-mode=ai --database=<name> security login-security - dbskiter --output-mode=ai --database=<name> security audit-log - dbskiter --output-mode=ai --database=<name> security high-risk - dbskiter --output-mode=ai --database=<name> security password-policy - dbskiter --output-mode=ai --database=<name> security weak-passwords - dbskiter --output-mode=ai --database=<name> security config
As a process D 48/100 · 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.
- 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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1135 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 48/100
- 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. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (db-security) differs from the folder (dbskiter-db-security)
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Execution cost. Instruction body is 1041 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (12 tags): a typed call is more reliable
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 1134: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 21 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 44.