Back to skill

Security audit

Wiro AI GitHub Action

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign because the reported external AI processing aligns with its stated purpose, while noting that repository diffs may be sent to an external service without a privacy warning.

Before installing, consider whether you are comfortable with repository diffs being sent to an external AI service, especially for private repositories. Skillspector scanned the listed component but marked its analysis partial because several references could not be resolved, so the available 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)

The pull-request workflow sends repository diffs to an external AI service without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The pull-request example automatically uploads the repository diff, excluding only package-lock.json, to Wiro AI without warning that proprietary code, personal information, or accidentally committed credentials could be disclosed to an external processor. External AI processing is the skill's stated purpose, which reduces suspicion of malicious intent, but the fork and Dependabot restrictions do not protect sensitive content in same-repository pull requests.

Content

No source excerpt is available for this finding.