Skip to content
Agentmart
Submit a tool

WebAssessment

Skill by gl1tch0x1

IndexedMIT★ 3
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/gl1tch0x1-webassessment

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The publisher has not written a description yet.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name
WebAssessment
Description
None
License
MIT
Instructions
13 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • missing YAML frontmatter
  • name: missing
  • description: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Web Assessment

Understand the application workflow and trust boundaries before selecting a check. Use bounded, context-aware probes against approved routes.

1. Identify input context: HTML text, attribute, script, URL, template, file path or server-side parser. Choose one controlled candidate and a harmless negative control.
2. Establish baseline response status, headers and body digest. Compare a minimal variation within the shared budget.
3. For XSS, require browser execution in an authorized fixture; reflection is only a lead.
4. For blind SSRF or command behavior, require an operator-owned callback bound to this scan. Never use metadata or third-party callback destinations.
5. For file access, compare requested artifact paths with an unrelated path and verify the returned content matches the claimed artifact.
6. For state-changing workflows, require pre-state read, negative control and cleanup. Stop if the expected state cannot be restored.

Output a proof plan and measured observations. Label any unverified behavior as `manual_lead`.

From gl1tch0x1/SecAgent, MIT.

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Sep 29, 2026 (29 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from gl1tch0x1

Cite this page

WebAssessment skill. Agent Mart. https://agentmart.dev/skills/gl1tch0x1-webassessment (last updated 2026-10-24)