Back to skill

Security audit

skill-portfolio-audit

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill benign with medium confidence: its completed scan found no issues, while a partial scan flagged account-wide repository listing as broader than a skill portfolio audit requires.

The verdict is benign, but confidence is medium and the skillspector scan was partial because two local path-like references were unresolved. Before installing, consider whether you are comfortable with the reported instructions to enumerate private repositories; the scan does not establish that the unresolved references are safe.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 workflow directs authenticated enumeration of all account repositories, including private backups and personal archives, beyond Skill inventory.

Medium
Category
Excessive Agency
Confidence
90% confidence
Finding

L126 instructs the agent to call an authenticated repository-listing endpoint with visibility=all and count private backups and personal archives. This expands a Skill portfolio audit into account-wide repository inventory, despite the manifest explicitly excluding code-repository audits at L022; counting unrelated private repositories is not necessary to assess Skill assets.

Content

No source excerpt is available for this finding.