Back to skill

Security audit

ia-document-review

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence; the completed scans found no AIG issues, while Skillspector flagged limited scope and purpose mismatches that the verdict treats as expected in context.

The verdict is benign, but benign does not mean risk-free. Before installing, consider whether the reported skill-testing and evaluation commands fit your needs for a document-review skill; the scan covered all three listed components.

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 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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied commands perform plugin validation and trigger testing. They do not visibly read or review documents, evaluate their organization or completeness, or check document claims against code. Although these commands could support maintenance of a document-review skill, the supplied chunk's actual purpose is testing that skill rather than performing its declared document-review function.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The supplied commands evaluate and diagnose the review skill itself, rather than perform the declared review of a document. This is a materially different operational purpose, not merely an implementation detail of document review. The implementation of distiller.py is not supplied, so additional behavior or resource access cannot be established.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
75% 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 144)May include surrounding context.

md
- Fix targeted sections, don't rewrite the whole document. If the structure is fundamentally broken, surface the structural problem and ask for permission to restructure.
- Flag missing sections in the review, but don't add them. The user decides what to include.
- Keep changes minimal. If a paragraph needs tightening, tighten it. Don't expand scope.
- Review inline. No separate review files or metadata sections.