Back to skill

Security audit

Apollo Research Synthesis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed markdown-only workflow guide for multi-agent research and synthesis, with no code execution, installs, credentials, network use, or persistence.

Before installing, consider whether you want this skill to activate on broad coordination or summarization prompts. It appears safe as a workflow guide, but narrower triggers would reduce unwanted influence on unrelated tasks.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases include broad, common coordination terms such as “综合”, “汇总”, and “Coordinator”, which are likely to appear in many ordinary prompts unrelated to this specific skill. This can cause unintended auto-activation, injecting the skill’s workflow constraints into unrelated tasks and altering agent behavior without clear user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The OpenClaw trigger list contains ambiguous single-word activators including “综合”, “汇总”, “Coordinator”, and “delegation”, with no contextual boundaries. Single-word triggers materially increase accidental invocation risk, which may steer workflows, delegation patterns, or isolation behavior in contexts where the user did not request this skill.

Content

No source excerpt is available for this finding.