ClawHub
Back to skill

Security audit

AANA Email Send Guardrail Skill

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill adds sensible pre-send checks for email and does not add code execution, persistence, or hidden data handling.

Install this if you want the agent to be more cautious before sending or scheduling email. Expect it to ask for explicit approval and to review recipients, attachments, sensitive content, and factual claims; use a configured checker only if you are comfortable with the redacted review payload described by the skill.

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 (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 107)May include surrounding context.

md
- whether it is needed,
- whether sharing is authorized.

Do not send attachments when the file is ambiguous, stale, private beyond scope, or not explicitly approved.

## Claim And Promise Rules

Static analysis

No suspicious patterns detected.