Back to skill

Security audit

discourse

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this skill as benign with medium confidence: the scanners report no AIG findings and generally positive results, with a privacy concern about search queries and one unresolved reference leaving the review incomplete.

The verdict is benign, not a guarantee of zero risk. Before installing, consider whether searches could reveal private details from your requests to third-party services, and note that Skillspector marked its analysis partial because a local path-like reference was unresolved.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The search workflow sends user-derived queries to third-party services without a privacy warning.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow instructs the agent to build topic-specific queries and execute them through external APIs or WebSearch. Although the destinations are described, the skill does not warn that search terms derived from the user's request will be shared with third parties, potentially exposing private context.

Content

No source excerpt is available for this finding.