sast-graphql

Detect GraphQL injection vulnerabilities in a codebase using a three-phase approach: recon (confirm GraphQL usage and find unsafe operation document assembly sites), batched verify (trace user input to those sites in parallel subagents, up to 3 candidate sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/graphql-results.md. If no GraphQL technology is found in Phase 1, later phases are skipped. Use when asked to find GraphQL injection, unsafe GraphQL document construction, or operation string injection bugs.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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

The body is highly actionable with concrete examples, explicit gates, and clear phased sequencing, though it leans verbose in the conceptual explanation sections. Progressive disclosure is weak because everything is inlined into one file with no external references.

Suggestions

Move the 'What is GraphQL Injection IS / is NOT' decision criteria and the full Phase 1/Phase 2 subagent prompt templates into a reference file (e.g. references/injection-criteria.md), leaving SKILL.md as a concise overview that links one level deep.

Trim or relocate the conceptual preamble that restates what GraphQL injection is at length, keeping only the minimal framing needed to disambiguate it from SQLi/NoSQL resolver issues.

Add a short 'Quick start / TL;DR' summary near the top so the three-phase flow and gate conditions can be grasped before the detailed prompts.

Dimension	Reasoning	Score
Conciseness	Most content is instructional and tight, but the 'What is GraphQL Injection IS / is NOT' sections and pattern lists restate concepts at length that Claude largely already knows; the body could be trimmed without losing clarity.	2 / 3
Actionability	Provides executable vulnerable/secure code snippets, exact file paths, and complete copy-paste-ready subagent instruction blocks with markdown output templates, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	The three phases are explicitly sequenced with validation gates ('Gate 1 — No GraphQL technology... skip Phases 2 and 3'), parallel-batching rules, and ordering constraints, giving clear checkpoints and feedback loops.	3 / 3
Progressive Disclosure	No references/scripts/assets bundle exists, so all content is inline in a single monolithic file; sections provide some structure, but referenceable detail (e.g., the IS/IS-NOT criteria, full subagent prompts) is not split out into one-level-deep files.	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.

The description is specific, third-person, and gives concrete actions plus an explicit 'Use when...' trigger, covering both what the skill does and when to invoke it. It is well-scoped to a distinct niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'recon (confirm GraphQL usage and find unsafe operation document assembly sites)', 'batched verify (trace user input to those sites in parallel subagents, up to 3 candidate sites each)', and 'merge (consolidate batch results)' — matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both 'what' (the three-phase detection approach and its outputs) and 'when' via an explicit 'Use when asked to find...' trigger clause, so both halves are present and explicit.	3 / 3
Trigger Term Quality	The closing 'Use when asked to find GraphQL injection, unsafe GraphQL document construction, or operation string injection bugs' provides good coverage of natural phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	It targets a clear niche — GraphQL operation-document injection — with distinct triggers unlikely to be confused with generic injection or file-handling skills, and the body further separates it from SQLi/NoSQL skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: utkusen/sast-skills
Path: sast-files/.agents/skills/sast-graphql/SKILL.md
Commit: db52227

Reviewed: about 20 hours 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.