Back to skill

Security audit

Refresh source context

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence; the scanners report no AIG findings, but Skillspector flags capabilities beyond the stated refresh purpose and only partially inspected the bundled helper.

The verdict is benign, not risk-free. Before installing, consider whether you need the extra source-collection and dependency-discovery capabilities. Confidence is medium, and the helper was only partially inspected, so the available evidence does not establish that every part is safe.

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
  • 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
Findings (4)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
Run the bundled Node 22+ helper `scripts/ink.mjs`, choosing new output paths:

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

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.

Dependency-manifest inspection and public registry discovery exceed the refresh-only purpose.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

At L296–L308, dependencyDocs reads local project manifests and resolves their dependencies into documentation URLs through public registry lookups implemented at L256–L270. This capability is exposed through the deps command at L324 and neither requires an existing snapshot nor contributes to comparing its previously collected sources; it also sends dependency names to external registries.

Content

No source excerpt is available for this finding.

The CLI supports first-time source collection without an existing snapshot.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest explicitly limits the skill to refreshing previously collected documentation and requires an existing snapshot. At L322–L323, the read and pack commands fetch arbitrary supplied public URLs or build a new pack without requiring any prior snapshot.

Content

No source excerpt is available for this finding.