graphql

GraphQL exploitation — introspection, injection, authorization bypass, and data exfiltration through GraphQL APIs.

Quality

81%

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

87%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, packed with copy-paste-ready GraphQL attack commands organized under clear sections. The main gap is the lack of validation/verification checkpoints in the workflow for batch and destructive operations.

Suggestions

Add validation checkpoints to the Workflow, e.g. 'Confirm introspection returns a schema before enumerating data' and 'Verify query success before chaining injection tests'.

Include a brief error-recovery note for common failures (disabled introspection, 401 on data queries) to close the feedback loop.

Dimension	Reasoning	Score
Conciseness	Lean and code-first throughout: brief section headers, short contextual inline comments, and executable commands with no padding or explanations of concepts Claude already knows.	5 / 5
Actionability	Fully executable, copy-paste-ready curl commands covering discovery, introspection, data enumeration, SQL injection, and batch abuse, with only the standard '<TARGET>' placeholder to replace.	5 / 5
Workflow Clarity	A six-step Workflow is sequenced, but this batch/destructive exploitation skill has no validation checkpoints (e.g. confirm introspection succeeded before enumerating), capping workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	A self-contained single file with no bundle dependencies, organized into clearly labeled sections and no nested references, which is appropriate for this scope.	5 / 5
	Total	18 / 20 Passed

Description

75%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 and distinctive, naming four concrete exploitation techniques within a well-defined GraphQL niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the activation guidance implicit.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user mentions GraphQL APIs, GraphQL injection, introspection, or gql endpoints.'

Add natural synonyms users say such as 'gql' or 'GraphQL SQLi' to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'introspection, injection, authorization bypass, and data exfiltration' — giving comprehensive coverage of the GraphQL exploitation domain.	5 / 5
Completeness	Provides a clear 'what' but no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Includes natural terms like 'GraphQL', 'GraphQL APIs', 'introspection', and 'injection', but omits common synonyms a user might say such as 'gql' or 'graphql sqli'.	4 / 5
Distinctiveness Conflict Risk	'GraphQL exploitation' is a clear, narrowly scoped niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/exploit/web/graphql/SKILL.md
Commit: 0cf691e

Reviewed: 2 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.