Security audit

story-telling

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward script-writing helper with disclosed local file use and fact-checking web searches, with no evidence of hidden or destructive behavior.

Before installing, be aware that using the fact-checking step can send parts of your story or factual claims to live web search. Use it with non-sensitive material, or ask the agent to skip or narrow web verification when working with private personal details.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Context-Inappropriate Capability

Medium

Confidence: 89% confidence
Finding: The skill instructs the agent to perform live web search/webfetch before adding factual claims, even though the skill’s declared purpose is script generation from a master document and local photos. Expanding capability scope to network retrieval introduces unnecessary exposure to prompt-injection, untrusted remote content, and unintended data flow outside the local author-provided materials.

Static analysis

No suspicious patterns detected.