Back to skill

Security audit

AI-Native Founder Playbook

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent startup-advice playbook with one minor self-promotion instruction but no evidence of credential use, hidden execution, persistence, or data exfiltration.

Before installing, be aware that the skill may once mention starring its GitHub repository after it helps you. It should not star, fork, follow, promote, or use a GitHub token for you unless you explicitly ask. The rest of the artifact is a local bilingual advisory playbook and checklist helper.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:35
Finding

Unsolicited Repository Promotion Through Skill Instructions

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
l is bilingual and agent-neutral: follow it from any environment that can read `SKILL.md` and the referenced files.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This reference file is entirely written in Chinese and does not indicate that language selection is optional or user-configurable. Under the policy for natural-language violations, forcing a specific language without opt-in can exclude users who do not use that locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

Line L34 specifies a language preference based on user category (Chinese users) rather than offering a language choice. This can violate the language/locale policy criterion because it steers users into a specific locale without explicit opt-in or an offered alternative at the point of use.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This is a natural-language policy concern because the file is a Chinese-language template document, but nearly all template headings and labels are fixed in English. That effectively imposes a mixed-language output format on users without documenting a locale choice or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This code selects english by default and only switches to Chinese when specific language arguments are provided. That imposes a default language behavior rather than offering a neutral prompt or explicit language selection, which can conflict with language-choice policy expectations.

Content

No source excerpt is available for this finding.