Skip to content
This repository was archived by the owner on Oct 2, 2026. It is now read-only.
This repository was archived by the owner on Oct 2, 2026. It is now read-only.

[0.2.0][M4] URL fetch category guard: robots.txt, PII stripping, redirect re-resolution (SSRF) #146

Closed

Description

@deghosal-2026

Type: Feature

Why

An arbitrary-URL fetch is a gatekeeper problem by itself: unfiltered content flows into the model's context, silently bypassing robots.txt, leaking PII, or being redirected to internal addresses (SSRF).

Why the user needs it

Users need structural checks on fetch content before it reaches the model — a tool category everyone underestimates.

How to address it

Ship a category guard for fetch: parse and obey robots.txt, strip PII from the response before it enters context, and re-resolve the final host after redirects against an internal-address blocklist.

What tests to add

  • robots.txt is actually enforced
  • PII is stripped from responses before entering context
  • Redirects to internal/metadata addresses are blocked (SSRF)

Source: dev.to feedback — https://dev.to/debashish_ghosal/i-stopped-trusting-ai-agents-with-tools-so-i-built-a-gatekeeper-26fb#comment-3d223

Activity

  1. added
    type/securitySecurity hardening and review
    v0.2.0v0.2.0 release milestone
    feedback/dev.toUser feedback from the dev.to article (I Stopped Trusting AI Agents With Tools)
    on Aug 14, 2026
  2. changed the title [-]URL fetch category guard: robots.txt, PII stripping, redirect re-resolution (SSRF)[/-] [+][0.2.0] URL fetch category guard: robots.txt, PII stripping, redirect re-resolution (SSRF)[/+] on Aug 14, 2026
  3. changed the title [-][0.2.0] URL fetch category guard: robots.txt, PII stripping, redirect re-resolution (SSRF)[/-] [+][0.2.0][M4] URL fetch category guard: robots.txt, PII stripping, redirect re-resolution (SSRF)[/+] on Aug 14, 2026
  4. deghosal-2026 commented on Aug 15, 2026

    @deghosal-2026
    MemberAuthor

    Closed by M4 implementation in commit ea0182a — engine/fetch_guard.py (FetchGuard/Config): scheme allowlist, robots.txt enforcement, PII/secret redaction, redirect re-resolution via urljoin against internal-address blocklist incl. protocol-relative //169.254.169.254 SSRF bypass (fail-closed). 100% module coverage.

  5. deghosal-2026 commented on Aug 15, 2026

    @deghosal-2026
    MemberAuthor

    🚀 Agent ToolTrust v0.2.0 release is live.

    📦 PyPI: https://pypi.org/project/agent-tooltrust/0.2.0/
    🏷️ Release: https://github.com/deghosal-2026/agent-tooltrust/releases/tag/v0.2.0
    📝 CHANGELOG: https://github.com/deghosal-2026/agent-tooltrust/blob/rel-0.2.0/CHANGELOG.md#020---2026-08-15

    All v0.2.0 milestones (M1-M8 + M7.5) are complete and shipped.

  6. added a commit that references this issue on Aug 15, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    component/adaptersFramework adaptersfeedback/dev.toUser feedback from the dev.to article (I Stopped Trusting AI Agents With Tools)priority/p1P1 — v0.2.0 targettype/securitySecurity hardening and reviewv0.2.0v0.2.0 release milestone

    Type

    No type

    Projects

    No projects

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions