Back to skill

Security audit

SEO Performance Audit

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill benign because the completed AIG scan found no issues and Skillspector reported one low-probability finding, though its review was partial.

The verdict is benign with medium confidence, but it is not a guarantee of safety. Consider that Skillspector inspected the artifact only partially: obfuscated instruction text limited several checks, and a local reference was unresolved. Review the skill’s instructions and decide whether it suits your needs before installing.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 230)May include surrounding context.

md
- It alerts on minor fluctuations without business context.
- It repeats unchanged findings from recent reports without saying already tracked.
- It skips duplicate checks.
- It recommends risky title/meta changes on a ranking page without warning.
- It ignores analytics/conversion data when available.

## Next step