ClawHub
Back to skill

Security audit

pharma-project-initiation-report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed report-generation workflow for pharmaceutical project research and does not show hidden or harmful behavior.

Before installing, users should understand that the skill will perform broad biomedical and business research queries and may use web checks to support the report. Review generated conclusions manually, especially patent/FTO, regulatory, safety, ROI, and GO/NO-GO sections, because these are high-impact business inputs even though the skill itself is not suspicious.

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
93% confidence
Finding

The markdown states that lang may be cn or en, but if unspecified it defaults to cn. This imposes a specific language choice by default rather than requiring explicit user selection, which is a natural-language locale policy concern under the stated rule.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.