Security audit

Adverse Event Narrative

Security checks for vulnerabilities and agentic risk

Overview

The skill is a local tool for drafting adverse-event safety report narratives, with clear medical-review warnings and no evidence of hidden network access, persistence, or credential handling.

Use de-identified case data and keep generated narratives under qualified drug-safety or physician review before any regulatory submission. Treat the English-focused examples and missing optional helper scripts as documentation limitations, not evidence of malicious behavior.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (3)

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The example API call hard-codes `language="en"`, and the documentation states the tool is optimized for English. For a general-purpose narrative generation skill, fixing the output language to English in usage examples can create a language/locale policy concern when no explicit user choice or opt-in is described.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: Under 'Language Requirements,' the file instructs users to 'Use clear, concise medical English.' This is a natural-language locale constraint, and the document does not state that English is optional, user-selected, or limited to a clearly justified regional workflow.

Static analysis

No suspicious patterns detected.