CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hunt-auth-bypass

Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024), partner-portal cross-IdP assertion reuse (Slack), WordPress XMLRPC bypassing SSO (Uber), JWT alg-confusion HS256/RS256 (Jitsi), JWT signature-validation skip (Linktree, Newspack), and token-audience confusion (Argo CD CVE-2023-22482). For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto; this skill covers JWT only inside SSO/SAML/token-trust bypass chains. SAML assertion-layer attacks (XSW, comment injection, signature stripping, XXE-in-assertion) are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy. Use when hunting auth bypass — see the Legacy-Protocol Matrix for branded-UI vs legacy-endpoint patterns.

Quality

87%

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

77%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.

An exceptionally actionable hunting guide with sequenced methodology and explicit validation gates, weakened by notable redundancy (narrative impact examples duplicating the citation list) and a monolithic single-file layout that inlines several large reference-worthy sections. Core operational content is non-obvious and well-organized.

Suggestions

Move the 12 Disclosed Report Citations and the niche Duende BFF section into references/ files (e.g. references/reports.md, references/duende-bff.md) and keep one-line pointers plus the highest-value payload inline, enabling progressive disclosure.

Cut the 'Real Impact Examples' scenarios that restate the Disclosed Report Citations, and trim payout-range commentary and the narrative engagement 'lesson' to their one-line takeaways.

Add natural trigger synonyms ('authentication bypass', 'login bypass', 'account takeover') to the description so users phrasing the need differently still surface the skill.

DimensionReasoningScore

Conciseness

The operational core (payloads, endpoint matrix, methodology) is dense and valuable, but padding is noticeable: payout-range commentary, three 'Real Impact Examples' narratives that largely restate the Disclosed Report Citations, and a narrative 'Lesson from a authorized engagement' paragraph. Mostly efficient but could be tightened, matching the 3 anchor rather than 2 since almost none of it explains concepts Claude already knows.

3 / 5

Actionability

Copy-paste-ready throughout: curl XMLRPC probes with exact methodCall bodies, Python for SAML signature stripping and JWT alg:none forging, a complete system.multicall credential-stuffing payload, grep/subfinder commands, and a per-tech matrix of exact legacy endpoints and SOAP operations. Matches the fully-executable 5 anchor.

5 / 5

Workflow Clarity

An 8-step sequenced methodology with impact-verification built into step 8, a 'Gate 0 Validation' checklist that gates report writing, and the matrix's 6-step 'How to use' with differential-response and rate-limit verification. Explicit validation steps and a checklist for a complex process match the 5 anchor.

5 / 5

Progressive Disclosure

A single ~450-line file with clear section headers but no bundle files at all; the Legacy-Protocol Matrix, the 12 report citations, and the Duende BFF section are content that clearly belongs in one-level-deep reference files. Structure is good (not the 2 anchor's 'minimal structure'), but the all-inline layout for a file this long matches the 3 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.

A highly specific, well-bounded description that names its attack subclasses concretely, gives explicit use-when guidance, and cleanly partitions scope against sibling hunting skills. The only gap is modest synonym coverage of natural trigger phrasings.

DimensionReasoningScore

Specificity

Enumerates multiple concrete attack subclasses — 'SAML XSW / parser-differential', 'SAML signature stripping', 'WordPress XMLRPC bypassing SSO', 'JWT alg-confusion HS256/RS256', 'token-audience confusion' — each with CVE/report attribution, giving comprehensive coverage of the skill's scope rather than vague domain naming.

5 / 5

Completeness

Explicitly answers 'what' (a hunting skill for auth-bypass vulnerabilities built from 12 disclosed reports across the listed subclasses) and 'when' ('Use when hunting auth bypass') with a concrete trigger phrase, mirroring the 5-anchor pattern of what-plus-when with explicit triggers.

5 / 5

Trigger Term Quality

Includes natural terms a user would say — 'auth bypass', 'SSO', 'SAML', 'JWT', 'XMLRPC', 'Use when hunting auth bypass' — but omits common phrasings like 'authentication bypass', 'login bypass', or 'account takeover'. Good coverage with a few natural synonyms missing, matching the 4 anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Actively delineates boundaries against sibling skills — 'For standalone JWT signature/crypto forging (alg:none, key confusion, kid/jku) see hunt-jwt-crypto' and 'SAML assertion-layer attacks... are owned by hunt-saml; this skill owns the broader cross-protocol auth-bypass taxonomy' — establishing a clear niche with minimal conflict risk.

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

elementalsouls/Claude-BugHunter

Path

skills/hunt-auth-bypass/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.