Back to skill

Security audit

Kosu

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the scanners found no reported malicious behavior and judged the skill’s behavior broadly purpose-aligned, though its remote skill-download step merits review.

Before installing, consider that the instructions can download and overwrite a local skill definition, and that remote content was not available for review. The scan was partial because a referenced local path was missing, so the evidence is incomplete.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The supplied code performs skill installation rather than queue management. Although the download comes from a Kosu-related domain, its only demonstrated behavior is modifying a local skill file; it makes no queue API calls. This is materially different from the declared purpose. The downloaded content is not supplied, so its behavior cannot be assessed, and the shown code does not execute it.

Content

No source excerpt is available for this finding.

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 31)May include surrounding context.

Save this skill locally:

bash
mkdir -p ~/.openclaw/skills/kosu
curl -s https://usekosu.com/skill.md > ~/.openclaw/skills/kosu/SKILL.md

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 32)May include surrounding context.

bash
mkdir -p ~/.openclaw/skills/kosu
curl -s https://usekosu.com/skill.md > ~/.openclaw/skills/kosu/SKILL.md

Or just read it directly from https://usekosu.com/skill.md. No install needed.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

bash
# Add item
curl -s "$BASE/items" -H "$AUTH" -H "Content-Type: application/json" \
  -d '{"url":"https://example.com/article"}'

# List queue (first 50)