CtrlK
BlogDocsLog inGet started
Tessl Logo

saml

SAML 2.0 attacks — XSW (XML Signature Wrapping) variants 1-8, comment injection, signature stripping, assertion forgery, IdP metadata abuse.

61

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/exploit/web/saml/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-organized, actionable attack playbook with concrete tooling and a feedback-looped PoC workflow; it is held just below top marks by minor padding, a few descriptive (non-executable) sections, and an all-in-one structure that could offload detail to reference files.

Suggestions

Add an explicit validation/checkpoint step to the PoC workflow (e.g. a concrete "confirm logged-in-as-target via /me or session cookie" test) to push workflow_clarity toward 5.

Give runnable steps or example requests for XSW2-8 and the metadata-abuse section instead of leaving them descriptive.

Move the Known exemplars and full XSW1-8 mechanics into a separate reference file referenced from SKILL.md to improve progressive_disclosure.

DimensionReasoningScore

Conciseness

Mostly lean and reference-shaped with concrete XML/bash snippets and a tight PoC pattern; only minor trimmable over-explanation remains (e.g. the opening "SAML is XML-based SSO used heavily in enterprise" line restates common knowledge).

4 / 5

Actionability

Provides concrete, executable guidance — a working decode one-liner (`echo ... | base64 -d | xmllint --format -`), named tools (SAML Raider, samltool.com, samlxss, Python saml2) and a step-by-step PoC pattern — though XSW2-8, self-signed, and metadata sections stay descriptive rather than giving runnable steps.

4 / 5

Workflow Clarity

Section 11 gives a clearly sequenced 7-step PoC workflow with built-in fallback branches ("If XSW fails... If still fails, try signature stripping"), which is a genuine feedback loop; it falls short of a 5 because explicit pass/fail validation checkpoints are light and several attack sections are presented as a catalog rather than a single end-to-end workflow.

4 / 5

Progressive Disclosure

Well-structured into 13 numbered sections plus a Cross-references block with clearly signaled one-level-deep pointers (to the upstream corpus Readme.md), and no nested/buried references; the main gap is that the exemplar list and detailed XSW mechanics are inlined in SKILL.md rather than split into separate reference files.

4 / 5

Total

16

/

20

Passed

Description

70%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 specific, well-keyworded description of a clearly distinct SAML attack niche, weakened only by the absence of an explicit "Use when..." trigger clause in the description field itself (trigger guidance is relegated to metadata).

Suggestions

Add an explicit 'Use when ...' clause to the description (e.g. 'Use when testing SAML 2.0 SSO flows for XSW, signature stripping, or assertion forgery.') to lift completeness above 3.

Mention 'SSO' and 'replay' directly in the description to broaden natural trigger coverage for users who phrase requests in those terms.

Rephrase the listed classes as concrete actions/verbs where possible to push specificity from 4 toward 5.

DimensionReasoningScore

Specificity

Enumerates several concrete attack classes — "XSW (XML Signature Wrapping) variants 1-8, comment injection, signature stripping, assertion forgery, IdP metadata abuse" — giving broad coverage, though a few known variants (replay, KeyInfo confusion) are absent so it is not fully comprehensive.

4 / 5

Completeness

The description field clearly states what the skill covers (the attack classes) but contains no explicit "Use when..." trigger clause; per the judging guideline a missing Use-when clause caps completeness at 3, and the when guidance lives only in the separate when_to_use metadata.

3 / 5

Trigger Term Quality

Strong natural keywords a SAML tester would actually say ("SAML 2.0 attacks", "XSW", "signature stripping", "assertion forgery", "IdP metadata"), supplemented by when_to_use terms like "saml sso identity provider"; missing a few synonyms/extensions but overall good coverage.

4 / 5

Distinctiveness Conflict Risk

"SAML 2.0 attacks — XSW variants 1-8, comment injection, signature stripping" carves out a clear, narrow niche with distinct triggers that would not reasonably fire for unrelated skills.

5 / 5

Total

16

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
PurpleAILAB/Decepticon
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.