Back to skill

Security audit

ASR Text Correction Safety

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused ASR/OCR text-correction safety guide with a local audit script, and I found no hidden persistence, exfiltration, destructive behavior, or privilege escalation.

Install if you want guidance and a local Node audit helper for ASR/OCR text-correction layers. When running scripts/audit.mjs, pass only correction modules you already trust to execute locally, because the script imports the module under test as part of the audit.

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
  • 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 (4)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 263)May include surrounding context.

md
node scripts/audit.mjs dict # 210,604 words → how many corrupted

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 316)May include surrounding context.

md
node scripts/audit.mjs dict # 210,604 words → how many corrupted

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 356)May include surrounding context.

md
node scripts/audit.mjs dict # 210,604 words → how many corrupted

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's activation description is broad enough to trigger on many general writing, reviewing, and debugging tasks that involve any post-recognition text rewriting. Over-broad invocation is a security concern because it can cause the agent to load unnecessary instructions and external guidance into unrelated workflows, increasing prompt-surface area and the chance of inappropriate influence on user tasks.

Content

No source excerpt is available for this finding.