Back to skill

Security audit

Research My Accounts

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: it found workflow and privacy-disclosure issues, while the completed AIG scan reported no findings; Skillspector coverage was partial.

Consider whether you are comfortable with the reported external sharing of account and contact lookup information, and with the risk that an email check may be up to 30 days old. The verdict is benign, but confidence is medium and Skillspector marks coverage partial because several local path-like references could not be resolved.

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
  • 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
Findings (2)

Reuses email checks up to 30 days old despite promising same-day verification.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The handoff rule explicitly reuses email checks up to 30 days old and omits those verification steps from the quote, conflicting with the same-day verification promise and final checklist. Following that rule could present stale addresses as ready, increasing bounced messages or outreach to reassigned mailboxes; this is primarily a data-integrity issue rather than a direct system compromise.

Content

No source excerpt is available for this finding.

The workflow sends user-provided account information to third-party services without a user-facing privacy disclosure.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow submits target company identifiers and contact lookup information through Scrollport to external providers, but its approval example explains spending rather than explicitly disclosing those data transfers. Such transfers are expected for account research and limited to relevant lookup fields, which reduces concern, but a nonpublic target list can still reveal confidential commercial interests without informed approval.

Content

No source excerpt is available for this finding.