Security audit

Startup Adaptation Strategist

Security checks for vulnerabilities and agentic risk

Overview

This Russian-market startup-analysis skill is mostly a markdown workflow, but it sends idea details to a fixed third-party API and asks to save candidate information to memory without clear consent or retention controls.

Install only if you are comfortable with startup idea descriptions being sent to the named third-party API and with candidate details being saved in agent memory. For confidential ideas, ask the agent to skip the API step, redact sensitive details, and get approval before writing anything to memory.

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 (4)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 282)May include surrounding context.
md
1. Читать `SKILL.md` в начале каждой сессии

Ae4

Medium

Category: analysis-evasion
Confidence: 80% confidence
Finding: Suspicious Unicode normalization or mixed-script content
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill instructs the agent to send idea descriptions to an external API endpoint, but provides no user consent flow, privacy notice, or data minimization guidance. In this context, idea_text may contain proprietary startup concepts or sensitive business information, so silent transmission to a third party creates confidentiality and supply-chain risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The entire skill is presented in Russian and repeatedly assumes Russian-language queries, Russian sites, and Russian output conventions, but it does not state that this locale is optional or user-selected. Under the language/locale policy, forcing a specific language without opt-in is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.