Back to skill

Security audit

adversarial-review-pipeline

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign because it found no AIG issues and its only reported concern was judged unlikely to indicate scope creep, though some references were unresolved and coverage is incomplete.

The verdict is benign with medium confidence, not a guarantee of safety. Skillspector inspected all nine listed components, but coverage is marked partial because two local path-like references could not be resolved; AIG completed with no findings. Consider whether the skill's review workflow fits your needs, and keep in mind that the unresolved references leave some evidence 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
  • 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)

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 153)May include surrounding context.

The file on disk is the deliverable. The completion message is a pointer.

An agent can report completion, summarize its findings confidently, and still have written nothing. This happens with subagents especially, but it is not limited to them.

bash