graphql-audit

GraphQL security hunting — introspection abuse, field suggestion enumeration (clairvoyance), batching DoS, IDOR via aliasing, auth bypass, injection via arguments, subscription abuse, depth/complexity bombs, and WAF bypass. Covers graphw00f fingerprinting, gqlmap, graphql-cop, and inql. Use when a target exposes a /graphql, /api/graphql, or GQL-over-HTTP endpoint.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

80%Weight 40%Scale 1-5

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 and token-efficient with concrete commands throughout, but it is a monolithic single file and—critically for a skill that performs batch and destructive operations—lacks validation/authorization checkpoints in its workflow, which caps workflow clarity.

Suggestions

Add explicit validation checkpoints to the workflow: an upfront authorization confirmation step and per-phase checks (e.g. verify response-time delta before escalating batching, confirm rate limiting is absent before alias bombing).

Provide the referenced tools/graphql_audit.sh as a bundle file in scripts/ or tools/, or remove the reference if the inline commands are the intended path, so referenced resources resolve.

Split the large report template and tool reference table into a separate references/ file with a clearly signaled "See REPORT_TEMPLATE.md" link to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is a dense sequence of copy-paste curl/python/gqlmap commands with almost no explanatory padding, assuming Claude's GraphQL competence and earning every token; the only prose lines ("GraphQL flips the threat model") provide apt threat-model framing rather than basic-concept explanation, matching the lean-and-efficient anchor.	5 / 5
Actionability	Every section provides fully executable, copy-paste-ready commands covering the common cases per phase (introspection probes, clairvoyance, batching/alias generators, IDOR curls, injection probes, wscat subscriptions), matching the fully-executable anchor.	5 / 5
Workflow Clarity	The Quick Kill Checklist supplies a clear ordered sequence and a chaining table plus kill signals, but the skill drives destructive/batch operations (batching DoS, alias bombs, OTP brute force, account takeover) without validation checkpoints between batch steps or any pre-engagement authorization confirmation; per the rubric's destructive/batch cap this limits workflow clarity to 3 even though sequencing is otherwise strong.	3 / 5
Progressive Disclosure	The file is well-sectioned but is a monolithic single document with no separate reference files; it references tools/graphql_audit.sh and output paths that do not exist as bundle files, and bulk content that could live apart (full report template, tool reference table) is inlined, matching the some-structure/could-be-better-organized anchor.	3 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

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, well-triggered, and complete, naming concrete attack classes, tools, and explicit use-conditions. It is a strong, low-conflict description whose only minor gap is breadth of natural synonyms.

Suggestions

Add a couple of natural synonyms users might say, e.g. "GraphQL API testing" or "GraphQL pentest", alongside the endpoint triggers to lift trigger-term coverage to 5.

Consider noting the authorization scope (e.g. "for authorized security testing") in the description to reduce misuse ambiguity without sacrificing specificity.

Dimension	Reasoning	Score
Specificity	The description enumerates eight concrete attack categories ("introspection abuse", "field suggestion enumeration (clairvoyance)", "batching DoS", "IDOR via aliasing", "auth bypass", "injection via arguments", "subscription abuse", "depth/complexity bombs", "WAF bypass") plus four named tools, matching the anchor for multiple specific concrete actions with comprehensive coverage.	5 / 5
Completeness	It explicitly states both what the skill does (security hunting across enumerated categories and tools) and when to use it ("Use when a target exposes a /graphql, /api/graphql, or GQL-over-HTTP endpoint"), matching the anchor that requires concrete trigger phrases for both what and when.	5 / 5
Trigger Term Quality	Natural endpoint trigger phrases are present ("/graphql", "/api/graphql", "GQL-over-HTTP endpoint", "security hunting") but the phrasing is endpoint-focused and omits common synonyms like "GraphQL API", "GraphQL pentest", or "GraphQL testing"; per anti-drift this sits between the good-coverage (4) and comprehensive-synonym (5) anchors, closer to 4.	4 / 5
Distinctiveness Conflict Risk	The GraphQL security-hunting niche is sharply defined with distinct endpoint-based triggers and named tooling, giving minimal overlap risk with other skills; this matches the clear-niche anchor.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (524 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: shuvonsec/claude-bug-bounty
Path: skills/graphql-audit/SKILL.md
Commit: 0826b13

Reviewed: 6 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.