Back to skill

Security audit

opencli-browser-sitemap

Security checks for vulnerabilities and agentic risk

Overview

The skill is a bounded browser-sitemap helper that may write local stale notes, but that behavior is disclosed and fits its purpose.

Install this if you want agents to use opencli sitemap context during browser tasks. Be aware it can create or edit local sitemap overlay notes and mark adapters suspect or broken, so review ~/.opencli/sites/<site>/sitemap/ if those persistent hints affect future automation.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (1)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Stale / Draft Notes

When you discover drift, write a small local note under the relevant page/workflow file or a draft file in the local overlay:

md
Stale note:

Static analysis

No suspicious patterns detected.