ClawHub
Back to skill

Security audit

AANA Tool Use Gate Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a safety-oriented instruction-only skill that tells agents to limit, review, and seek approval for risky tool use rather than expanding authority.

This skill is appropriate if you want an agent to pause and review risky tool use. It may make the agent ask for confirmation more often before private-data access, external sends, destructive changes, financial actions, deployments, or privileged operations.

A.I.G

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

SkillSpector

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 (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 128)May include surrounding context.

md
- the user did not authorize a risky action,
- the target scope is ambiguous,
- the tool could harm unrelated files, accounts, systems, or people,
- the action would bypass consent, policy, review, or safety boundaries,
- the request involves credential theft, fraud, evasion, harassment, exfiltration, or unauthorized access,
- a qualified professional, administrator, or verified system must review the action first.

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 77)May include surrounding context.

md
- the answer can be given from already available evidence,
- the tool would collect private data not needed for the task,
- the user asked for a conceptual explanation only,
- the tool would expand scope beyond the user request,
- a lower-risk tool or read-only step is enough.

Prefer:

Static analysis

No suspicious patterns detected.