Back to skill

Security audit

supply-chain-advisory

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill suspicious because a scanner found that its incident-response guidance may save sensitive environment credentials to a temporary file without a privacy warning.

Review this skill before installing. Consider whether you are comfortable with its reported environment-capture guidance; it may place credentials in a temporary file. The scan was partial because several local references could not be matched to bundled files, 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
  • 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)

Environment capture writes potentially sensitive credentials to a temporary file without a privacy warning.

Medium
Category
Output Handling
Confidence
98% confidence
Finding

The environment snapshot can copy API tokens, cloud credentials, and database passwords into plaintext under /tmp, where default permissions may make it readable by other local users. The timestamp-based filename and shell redirection also create a potential symlink attack surface on shared systems. Capturing evidence is legitimate incident-response work, but doing so during a suspected credential-theft incident without access controls or retention guidance creates another sensitive artifact that must be protected.

Content

No source excerpt is available for this finding.