CtrlK
BlogDocsLog inGet started
Tessl Logo

sast-xss

Detect Cross-Site Scripting (XSS) vulnerabilities in a codebase using a three-phase approach: recon (find HTML/JS/DOM sink sites), batched verify (trace user input to sinks in parallel subagents, 3 sink sites each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/xss-results.md. Use when asked to find XSS or cross-site scripting bugs.

67

Quality

81%

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

The canonical home for this skill is sast-xss in utkusen/sast-skills

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 highly actionable, well-sequenced SAST workflow with strong code examples and clear phase gating, weakened mainly by redundant pattern listings and an introductory primer that pads the token budget. Splitting the framework catalogs into a reference file would improve both conciseness and progressive disclosure.

Suggestions

Remove the 'What is XSS' and 'XSS Types' primer — Claude already knows these — and let the body open with the actionable sink catalogs.

De-duplicate the per-framework sink patterns: keep one canonical catalog (ideally in a references/sinks.md file) and have Phase 1 reference it instead of restating the list inline.

Add an explicit validation step in Phase 3 to check each xss-batch-*.md is well-formed and classified before merging, and consider moving the multi-language vulnerable/secure examples into a reference file to shrink SKILL.md.

DimensionReasoningScore

Conciseness

The body is mostly substantive domain reference, but it opens with a 'What is XSS' / 'XSS Types' primer Claude already knows and duplicates the per-framework sink catalog nearly wholesale — once in 'What XSS IS' and again in the Phase 1 search list — so it could be tightened; not severe enough for 2, but the redundancy and conceptual padding keep it off 4.

3 / 5

Actionability

Provides copy-paste-ready subagent prompts with exact output templates, concrete vulnerable/secure code across a dozen languages, and explicit sink APIs and source lists to search for — fully executable guidance covering common cases.

5 / 5

Workflow Clarity

Three phases are clearly sequenced with explicit cross-phase dependencies and an upfront validation gate (skip Phase 2/3 when recon finds zero sinks); Phase 2 itself verifies Phase 1 candidates. Missing an explicit 'verify batch output well-formedness before merge' checkpoint, so just short of 5.

4 / 5

Progressive Disclosure

No bundle/reference files exist and the ~600-line body inlines large pattern catalogs (sink lists and vulnerable/secure examples across 10+ frameworks) that could live in a separate references file; section headers give decent structure, but content that should be split is inline with no file-based navigation.

3 / 5

Total

15

/

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 strong, specific description that clearly states both capability and trigger conditions in third person, with concrete phase breakdown and prerequisites. The only minor gap is trigger-term breadth beyond the XSS/cross-site scripting pair.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across a three-phase approach — 'recon (find HTML/JS/DOM sink sites)', 'batched verify (trace user input to sinks in parallel subagents, 3 sink sites each)', and 'merge (consolidate batch results)' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers what ('Detect Cross-Site Scripting vulnerabilities... three-phase approach', prerequisites, output path) and when ('Use when asked to find XSS or cross-site scripting bugs') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes the natural synonyms users say — 'XSS' and 'cross-site scripting bugs' — but omits related phrasings like 'script injection' that a user might also use; good coverage with a few natural terms missing, so above the midpoint but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (XSS specifically), names its prerequisite ('Requires sast/architecture.md... run sast-analysis first') and output file, and uses distinct XSS-only triggers, giving minimal overlap with sibling SAST skills.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (622 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
utkusen/sast-skills
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.