Back to skill

Security audit

read-everything-or-else

Security checks for vulnerabilities and agentic risk

Overview

ClawScan gives this skill a benign verdict with medium confidence: the scanners report no AIG findings, but Skillspector flags risks in its coverage checks and the scan is marked partial.

Consider whether the skill’s file access fits your needs, and whether its coverage limitations matter for your use. Skillspector inspected all five listed components, but marked its analysis partial because several local references could not be resolved; the benign verdict is not a guarantee that the skill is risk-free.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (3)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

An empty manifest passes the audit despite reporting 0% coverage.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

A header-only manifest produces no gaps, so the audit returns success and explicitly authorizes a completion claim despite checking no source material. Although the scanner normally rejects an empty collection, the auditor independently accepts an empty or truncated manifest, bypassing the skill's central completion gate and enabling misleading assurance.

Content

No source excerpt is available for this finding.

The scanner excludes entire directory trees by default despite the manifest's promise of exhaustive coverage with nothing skipped.

Medium
Category
Excessive Agency
Confidence
93% confidence
Finding

L146-L150 prune directories in SKIP_DIRS unless the caller supplies --all, including potentially substantive content in dist, build, target, .vscode, and .idea. Although these exclusions are logged, their contents never become manifest checklist units, so completing every generated unit does not establish the exhaustive coverage of the user's target promised by the skill.

Content

No source excerpt is available for this finding.