ClawHub
Back to skill

Security audit

species_identification_sequence_blast_annotation_tool

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its BLAST annotation purpose, but a crafted OTU table can make one script write result files outside the chosen output folder.

Review this before installing if you will run OTU tables from other people. Use a dedicated output directory, avoid private sequence data unless NCBI submission is acceptable, and sanitize or inspect sample column names so they cannot contain ../, absolute paths, or other filename tricks.

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
Confidence
84% confidence
Finding
The quick-call phrases are broad and generic enough that they could cause the skill to be invoked unintentionally during normal conversation, especially when users mention BLAST annotation in a descriptive rather than imperative way. In an agent setting, ambiguous invocation increases the chance of unexpected tool guidance or downstream actions being triggered without sufficiently explicit user intent.

Static analysis

No suspicious patterns detected.