ClawHub
Back to skill

Security audit

Biotech BP Architect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a writing and critique aid for biotech fundraising decks, with no scripts, network behavior, persistence, credential use, or hidden high-impact actions found.

Before installing, treat this as a deck-writing aid rather than legal, regulatory, or investment advice. Use it only with materials you own or are authorized to share, and review any confidentiality text with counsel when the deck is sensitive or jurisdiction-specific.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file states that confidential decks must include a standalone page with both Chinese and English text, which imposes a specific language requirement. This is a natural-language locale policy issue because the skill does not offer a language choice or explain why bilingual Chinese/English output is required for all users.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.