CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

api-audit

Audit REST, GraphQL, and RPC APIs against the OWASP API Security Top 10 (2023). Use when the user mentions 'API security,' 'API audit,' 'BOLA,' 'broken object level authorization,' 'BFLA,' 'function-level authorization,' 'mass assignment,' 'API rate limiting,' 'GraphQL security,' 'REST security,' 'API authentication,' 'API authorization,' 'excessive data exposure,' or needs to review API endpoints for security weaknesses.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A strong, expert-level audit skill: fully actionable checklists with exact grep patterns and executable validation commands, a rigorously sequenced workflow with adversarial verification and coverage critique baked in, and a clean split between inline working content and one-level-deep references. The only weakness is minor redundancy in the cross-referencing prose.

DimensionReasoningScore

Conciseness

The body is dense with expert-level checks and never tutors Claude on basics, but the owasp-audit distinction is stated twice (opening paragraph plus the Cross-references list) and the final References section re-lists files already linked inline. Anchor 4 (efficient, minor trims possible) fits better than 5 because a few tokens do not earn their place.

4 / 5

Actionability

Guidance is fully executable: exact grep strings ('jwt.verify', 'Bearer ${process.env', 'findByIdAndUpdate(id, req.body)'), concrete vulnerable code patterns, a copy-paste curl baseline/attack pair, runnable validators ('node references/validate-findings.mjs findings.json'), and a complete report template. Matches the anchor-5 example of copy-paste-ready commands covering the common cases; not 4 because there are no gaps in the concrete guidance.

5 / 5

Workflow Clarity

A 7-step workflow with 'Run in order. Do not skip to the checklist.', explicit validation checkpoints (per-finding refutation pass, coverage critic, findings.json validated before prose, runtime fix verification), and feedback loops (three-verdict system, re-validation on material change). This is the anchor-5 pattern of sequence + explicit validation + error-recovery loops; the missing-validation cap does not apply.

5 / 5

Progressive Disclosure

The working checklist stays inline while deep material (GraphQL playbook, verification procedure, severity calibration, findings format) is pushed to clearly signaled one-level-deep references, all of which resolve to real bundle files; even orchestration.md and to-sarif.mjs are reachable one level down via recon-and-coverage.md and findings-format.md. Anchor 5 (appropriately split, easy navigation) fits; not 4 because no content is misplaced or buried.

5 / 5

Total

19

/

20

Passed

Description

95%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.

An excellent description: third-person, concrete about what it does, with an explicit and exhaustive 'Use when' trigger list covering acronyms, synonyms, and plain-language variants. Its only limitation is relying on one action verb ('audit') rather than enumerating several specific capabilities.

DimensionReasoningScore

Specificity

'Audit REST, GraphQL, and RPC APIs against the OWASP API Security Top 10 (2023)' names a concrete action, three API surface types, and a specific framework — more concrete than anchor 3's 1-2 actions, but it rests on a single verb rather than the multiple distinct actions of anchor 5.

4 / 5

Completeness

Explicitly answers both questions: the first sentence states what the skill does, and 'Use when the user mentions [list] or needs to review API endpoints for security weaknesses' states when with concrete trigger phrases — the anchor-5 pattern verbatim. Not 4 because the 'when' clause is already fully explicit.

5 / 5

Trigger Term Quality

The trigger list is comprehensive and natural: 'API security,' 'API audit,' 'BOLA,' 'broken object level authorization,' 'BFLA,' 'mass assignment,' 'API rate limiting,' 'GraphQL security,' 'REST security,' 'API authentication,' 'excessive data exposure,' covering synonyms, acronyms, and expanded forms. Matches anchor 5 (comprehensive natural terms including synonyms); anchor 4's 'a few natural terms missing' does not apply.

5 / 5

Distinctiveness Conflict Risk

A clear niche (OWASP API Security Top 10 auditing) with API-specific triggers like BOLA, BFLA, and mass assignment that a generic web-audit or dependency-audit skill would not claim. Minimal conflict risk; matches anchor 5.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

briiirussell/cybersecurity-skills

Path

skills/api-audit/SKILL.md

Reviewed

Table of Contents

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.