ClawHub
Back to skill

Security audit

Rec. Letter Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple recommendation-letter drafting helper with minor documentation quality issues but no evidence of hidden, destructive, persistent, or exfiltrating behavior.

Before installing, note that recommendation letters may contain sensitive applicant information, so review prompts and generated drafts carefully and avoid providing unnecessary personal data. The author should also fix the incomplete description and ambiguous activation wording, but the current artifacts do not show hidden or high-impact behavior.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill’s activation guidance is ambiguous and partially malformed ('Use this skill when the task needs Helps faculty and mentors draft standardized recommendation letters for.'), which weakens scope boundaries and can cause the agent to invoke the skill for ill-defined writing tasks. In a skill that may process sensitive applicant information and run local scripts, unclear invocation criteria increase the risk of misuse, inappropriate handling of personal data, or execution in contexts the author did not intend.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.