Name: identify-security-vuln-discussion
Rating: 91.2 (1 reviews)
Author: netwrix

identify-security-vuln-discussion

Screen GitHub issues and comments for inadvertent security vulnerability disclosure. Use when: (1) A new issue is created, (2) An issue body is edited, (3) A comment is added or edited, (4) Part of issue intake pipeline. Prevents bypass by editing clean issues to add vulnerabilities later. If a vulnerability is detected in title/body, closes the issue and tags @netwrix/security. If detected in a comment, deletes the comment and posts a security notice.

2.00x

Quality

88%

Does it follow best practices?

Impact

96%

2.00x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

This is a well-structured, highly actionable security screening skill with clear executable commands and distinct action paths for different scenarios. Its main weakness is moderate verbosity—the 'Important Principles' and 'Notes' sections contain overlapping guidance and some points that Claude would naturally understand. The workflow is clearly sequenced with appropriate branching logic for different vulnerability locations.

Suggestions

Consolidate the 'Important Principles' and 'Notes' sections into a single concise 'Constraints' section, removing redundant points (e.g., merge 'Check everything' and 'Check ALL comments every time').

Remove guidance Claude already knows, such as 'Authors may not realize they're disclosing sensitive information' and the explanation of why issue titles are visible in search results.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary verbosity: the 'Important Principles' and 'Notes' sections overlap significantly (e.g., 'check everything' vs 'check ALL comments every time'), and some points like explaining why titles are sensitive or that authors may not realize they're disclosing information are things Claude already understands. The security indicators list and action steps are well-structured but could be tighter.	2 / 3
Actionability	The skill provides fully executable gh CLI commands for every action (fetching comments, posting comments, closing issues, deleting comments via API), exact comment text to post verbatim, and clear report output formats. Every step is copy-paste ready with proper variable substitution.	3 / 3
Workflow Clarity	The process is clearly sequenced (fetch → evaluate → act) with three distinct action paths (SAFE, title/body concern, comment concern), each with numbered steps. The workflow includes explicit branching logic, and the notes clarify pipeline continuation behavior (stop after closing issue, continue after deleting comment). The distinction between title/body vs comment vulnerabilities provides clear decision points.	3 / 3
Progressive Disclosure	The content is a single monolithic file with no references to supporting documents. While the skill is moderately complex, the 'Notes' and 'Important Principles' sections could be consolidated, and the workflow configuration section at the end feels like it belongs in a separate setup/configuration document rather than in the skill body itself. However, for a standalone skill with no bundle, the organization is acceptable.	2 / 3
	Total	10 / 12 Passed

Description

100%

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

This is an excellent skill description that clearly defines a specific niche (screening GitHub issues for security vulnerability disclosure), lists concrete actions taken in response, and provides explicit trigger conditions via a well-structured 'Use when' clause. It covers edge cases (edit-based bypass) and specifies distinct remediation actions for different contexts (issue vs. comment), making it both comprehensive and distinctive.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: screens issues/comments for vulnerability disclosure, closes issues, tags @netwrix/security, deletes comments, posts security notices, and prevents bypass via editing.	3 / 3
Completeness	Clearly answers both 'what' (screens for inadvertent security vulnerability disclosure, closes issues, deletes comments, tags security team) and 'when' (explicit 'Use when' clause with four specific trigger scenarios).	3 / 3
Trigger Term Quality	Includes natural trigger terms users/systems would use: 'GitHub issues', 'comments', 'security vulnerability disclosure', 'issue created', 'issue body edited', 'comment added', 'issue intake pipeline'. These cover the natural language around this workflow well.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche: screening GitHub issues specifically for inadvertent security vulnerability disclosure. The combination of GitHub issues + security vulnerability screening + specific remediation actions (close, delete, tag) makes it very unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

90%

Warnings & errors only

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

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: netwrix/docs
Commit: 6b797b3

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.