Back to skill

Security audit

Saas Indie Hacker Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown coaching skill for indie SaaS founders, with no executable code or hidden system-level behavior.

This skill is reasonable to install for indie SaaS coaching. Be aware it may activate on broad SaaS or MRR-related prompts, and treat its business, tax, legal, and valuation advice as general guidance rather than professional advice.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains very broad terms such as "MRR" and related startup jargon that can appear in many unrelated business conversations. This can cause the skill to activate outside its intended niche, leading to context hijacking, irrelevant guidance, or accidental override of a more appropriate skill in multi-skill routing.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The engagement criteria are expansive and primarily describe when to engage, but do not define crisp non-activation boundaries beyond a few scam-related exclusions. In practice, this increases the chance of over-triggering on adjacent startup, marketing, pricing, or hiring requests where a different skill or general assistant behavior would be safer and more accurate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.