Back to skill

Security audit

resurface

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because a scanner reported that it saves complete snapshots of authenticated pages without a sensitive-data warning; the overall review has medium confidence and scan coverage is incomplete.

Before installing, consider whether the skill may handle authenticated pages containing personal or sensitive information. Skillspector recommends minimizing and sanitizing saved snapshots and setting access and retention limits. The scan is partial: a static analysis limit was reached and many referenced paths were not present in the scanned artifact, so the results do not establish that the skill is safe.

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
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Authenticated page snapshots are saved locally without a sensitive-data warning.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The skill requires saving complete DOM snapshots of every discovered page, including pages accessed after user authentication, without specifying redaction, access controls, or retention limits. These snapshots can contain personal records, financial data, hidden CSRF tokens, or other sensitive values and could be exposed through source-control commits, shared development artifacts, or agent tooling; authenticated whole-site crawling increases the exposure.

Content

No source excerpt is available for this finding.

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SKILL.md (reported line 585)May include surrounding context.

md
- [ ] **Data Integrity:** 100% of data values match the legacy portal (verified with snapshot unit tests in Vitest).
- [ ] **Native Sessions Preserved:** Navigating routes does not invalidate authentication or drop cookies.
- [ ] **Fallback Toggle:** User can switch back to the "Original View" anytime with a persistent setting toggle.
- [ ] **Least-Privilege Permissions:** Manifest strictly requests host permissions for the targeted domain only.