Back to skill

Security audit

Quick Converter

Security checks for vulnerabilities and agentic risk

Overview

This is a lightweight offline conversion helper with no executable code or requested system access, though its static rates and IST time default can be misleading for real-world decisions.

Install only for casual offline estimates. Verify live currency and crypto prices before banking, trading, or purchasing decisions, and explicitly provide the timezone for scheduling or deadline questions because the skill defaults to IST/Ahmedabad and contains stale March 2026 reference assumptions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The phrase "Use this skill anytime for instant, no-internet conversions" is an overly broad invocation cue in a markdown skill description. It does not clearly limit when the skill should or should not activate, which could cause unintended invocation during ordinary chat involving numbers or time references.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The listed trigger phrases include highly abstract templates like "convert X Y to Z" and "how many Z in X," which are not specific enough to the domain and lack boundaries or negative examples. Such patterns can collide with common everyday speech and make activation criteria ambiguous.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Defaulting to IST/Ahmedabad without user opt-in can cause the agent to give incorrect time calculations when the user is in another locale or expects local time. While not a traditional exploit vector, it can materially mislead users about schedules, deadlines, or event timing, especially because the skill presents the locale assumption as a default operational behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.