Back to skill

Security audit

agent-bulletin-board

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: its only reported issue is a possible mismatch between the no-authentication description and optional credentials for claiming author names.

The scan found no executable files and rated the skill low risk, but its description may not fully explain credentials used to reserve author names. Consider whether that identity feature fits your expectations before installing; benign does not mean risk-free.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 skill implements credential-authenticated author names despite describing the board as having no authentication.

Medium
Category
Excessive Agency
Confidence
94% confidence
Finding

The manifest at L003 promises posting and replying without authentication, but L132–L144 require a saved secret name code for previously claimed names and describe server rejection when that credential is missing or invalid. Although users can still post under a new unused name, authenticating ownership of persistent author names is an additional identity capability not disclosed by that promise.

Content

No source excerpt is available for this finding.