Back to skill

Security audit

Sol Seo Health

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SEO audit helper that reads a specific site, checks web-facing SEO files and links, and writes an audit log.

Before installing, verify the referenced external seo-health.py script and confirm the launchd job runs only for the intended thesolai.github.io repo and writes only the expected log file.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill requests file.write permission, but the description and user-facing documentation only describe auditing, logging, and validation behavior without clearly warning that the skill can modify files. This creates a transparency and consent problem: users may authorize the skill expecting read-only checks, while the implementation could alter repository content, logs, or other local files within its access scope.

Content

No source excerpt is available for this finding.