CtrlK
BlogDocsLog inGet started
Tessl Logo

database-security

Use for authorized database security assessment covering PostgreSQL/MySQL/MSSQL/Mongo/Redis exposure, authz, UDF/command paths, and misconfiguration review.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A terse, well-structured assessment skeleton that assumes competence and avoids concept bloat, but it stays at the checklist level without executable commands or an explicit findings-validation feedback loop. The misconfig reference partly duplicates inline content.

Suggestions

Add concrete executable checks — e.g. SQL like `SHOW VARIABLES LIKE 'secure_file_priv'` or `EXEC sp_configure 'xp_cmdshell'` — so the guidance is copy-paste ready, not just a list of what to inspect.

Add an explicit validate/feedback loop for assessment findings (confirm exploit safely → document → route downstream), since database operations warrant a verification checkpoint per the rubric.

Keep the misconfig checklist only in references/db-misconfig-checklist.md and reference it as a markdown link, removing the duplicate inline copy in the workflow section to avoid content that should live in the bundle being inline.

DimensionReasoningScore

Conciseness

Lean throughout — short checklist lines, a compact tool table, and no concept padding; assumes Claude knows xp_cmdshell, COPY PROGRAM, UDF, file_priv and load_file without explanation.

3 / 3

Actionability

Names concrete items to check (file_priv, xp_cmdshell, load_file, 0.0.0.0 binding) but gives no executable commands or SQL queries to actually check them, so guidance is incomplete rather than copy-paste ready.

2 / 3

Workflow Clarity

A clear sequence exists (ACT: 暴露面 → 认证 → 授权 → 配置 → 利用链) plus a safety gate and completion self-check, but there is no explicit validate→fix→retry feedback loop, which the rubric requires for database operations.

2 / 3

Progressive Disclosure

A one-level reference (references/db-misconfig-checklist.md) is signaled, but its checklist is duplicated inline in the workflow section and the path is a plain code span rather than a clearly-signaled link.

2 / 3

Total

9

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-triggered description that names concrete databases and attack surfaces with an explicit 'Use for' invocation clause. It cleanly answers both what the skill does and when to use it.

DimensionReasoningScore

Specificity

Lists multiple concrete targets — five named databases (PostgreSQL/MySQL/MSSQL/Mongo/Redis) and specific assessment areas (exposure, authz, UDF/command paths, misconfiguration) rather than vague language.

3 / 3

Completeness

Explicitly states what ('authorized database security assessment covering...') and when via the 'Use for' trigger clause, satisfying both what and when.

3 / 3

Trigger Term Quality

Good natural-term coverage a user would say ('database security assessment', product names, 'misconfiguration', 'exposure'); 'authz' and 'UDF' are specialist jargon but the DB names and security framing carry natural triggers.

3 / 3

Distinctiveness Conflict Risk

Clear niche (database security assessment) with distinct DB-specific triggers; unlikely to fire for non-database skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zhaoxuya520/reverse-skill
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.