ClawHub
Back to skill

Security audit

Remix V2 Forms Review

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Remix form review guide with a disclosed, specific cross-reference to related review documentation and no executable behavior.

Before installing, confirm you trust the referenced sibling review documents in your local skill set, because this skill asks the agent to consult them during reviews. Otherwise, its behavior is limited to code-review guidance for Remix v2 forms.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

md
3. **Form-method check** — **Pass:** Before flagging missing intent, missing `encType`, missing `redirect`, or missing pending state, you have confirmed the form is `method="post"` (or `put|patch|delete`). GET forms are legitimate for search/filter and trigger loaders, not actions — applying POST-form rules to them is a false positive.

4. **Protocol** — **Pass:** You completed the Pre-Report Verification Checklist in [review-verification-protocol](../../../beagle-core/skills/review-verification-protocol/SKILL.md) for this review.

## Additional Documentation

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 118)May include surrounding context.

md
3. **Form-method check** — **Pass:** Before flagging missing intent, missing `encType`, missing `redirect`, or missing pending state, you have confirmed the form is `method="post"` (or `put|patch|delete`). GET forms are legitimate for search/filter and trigger loaders, not actions — applying POST-form rules to them is a false positive.

4. **Protocol** — **Pass:** You completed the Pre-Report Verification Checklist in [review-verification-protocol](../../../beagle-core/skills/review-verification-protocol/SKILL.md) for this review.

## Additional Documentation

Static analysis

No suspicious patterns detected.