common-security-audit

Probe for hardcoded secrets, injection surfaces, unguarded routes, business logic flaws, and platform-specific weaknesses across backend (Node, Go, Java, Python, Rust), frontend (React, Angular, Vue), and mobile (iOS, Android, Flutter) codebases. Use when performing security audits, vulnerability scans, secrets detection, or penetration testing.

Quality

86%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

A concise, well-structured audit overview that makes good use of progressive disclosure and real reference files. Its weaker spots are uneven inline actionability (several sections rely entirely on references) and missing validation feedback loops for destructive remediation steps.

Suggestions

Add at least one inline executable command per core section (secrets scan, log leakage, injection/auth) instead of routing everything to references/implementation.md, so the skill stands alone for the highest-priority checks.

Add explicit validate-fix-retry checkpoints for destructive/batch remediation (e.g., rotate secret -> purge from history -> re-scan to confirm no matches remain).

Make the audit workflow order explicit (e.g., 1. secrets -> 2. logs -> 3. injection -> 4. dependencies -> 5. infra -> 6. frontend -> 7. mobile -> 8. business logic) so the numbered P0/P1 sections read as a sequence rather than a checklist.

Dimension	Reasoning	Score
Conciseness	The body is lean: priorities, terse command snippets, and a scoring table, with no padding that explains concepts Claude already knows; nearly every token earns its place.	3 / 3
Actionability	Sections 4, 6, and 8 give concrete executable commands, but sections 1, 2, 3, 5, and 7 only point to "See references/implementation.md" without any inline command, leaving several core actions incomplete inline.	2 / 3
Workflow Clarity	A priority structure (P0/P1/P2) and a scoring-impact table provide sequencing, but destructive/batch operations such as secret rotation and CVE remediation lack explicit validate-fix-retry checkpoints, capping clarity at 2.	2 / 3
Progressive Disclosure	The body is an overview pointing to one-level-deep, well-signaled references (implementation.md, mobile-audit.md, REMEDIATION.md), all of which exist in the bundle, with content appropriately split for navigation.	3 / 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.

A strong, third-person description that specifies concrete audit actions across backend/frontend/mobile and pairs them with explicit use-when triggers. It is distinct, complete, and free of vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Probe for hardcoded secrets, injection surfaces, unguarded routes, business logic flaws") and enumerates specific platforms across backend, frontend, and mobile, matching the "multiple specific concrete actions" anchor.	3 / 3
Completeness	Clearly answers both what ("Probe for hardcoded secrets..." across named codebases) and when ("Use when performing security audits, vulnerability scans, secrets detection, or penetration testing"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Natural user-facing terms appear via "Use when performing security audits, vulnerability scans, secrets detection, or penetration testing," backed by metadata keywords (pentest, Dockerfile, injection probe); good coverage of terms users would say.	3 / 3
Distinctiveness Conflict Risk	Scoped to a clear niche (multi-platform security auditing) with platform-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: HoangNguyen0403/agent-skills-standard
Commit: 611f52a

Reviewed: 9 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.