ClawHub
Back to skill

Security audit

osascript-email

Security checks for vulnerabilities and agentic risk

Overview

This macOS Mail.app email skill is mostly purpose-aligned, but its ready-to-use helpers build executable AppleScript from insufficiently validated fields, creating a real review concern before installation.

Install only if you understand that this can silently send mail from a configured macOS Mail.app account. Treat recipient, sender, subject, body, and attachment path values as trusted-only unless the helper is rewritten to pass values as data rather than AppleScript source, validate addresses and paths, and require explicit confirmation before sending or attaching files.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/send_email.py:22
Finding

AppleScript Injection Through Unsafely Interpolated Email Fields

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
references/attachments.md:22
Finding

AppleScript Injection in Documented Attachment Helper

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/send_email.py (reported line 45)May include surrounding context.

python
end tell
return "sent"'''

    result = subprocess.run(
        ["osascript", "-e", script],
        capture_output=True,
        text=True

Excessive Permissions

Low
Category
Privilege Escalation
Confidence
80% confidence
Finding

Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

md
| Email lands in Drafts | `send m` not reached (script errored before) | Check escape characters |
| `execution error: Mail got an error: Invalid recipient` | Address typo | Verify recipient address |
| Email sends but empty body | Newline escape issue in content string | Use Python helper instead |
| `returncode != 0` with no stderr | osascript permission denied | Grant Automation permission: **macOS Ventura+**: System Settings → Privacy & Security → Automation; **older macOS**: System Preferences → Security & Privacy → Automation |

---