Back to skill

Security audit

Dunbar's Number

Security checks for vulnerabilities and agentic risk

Overview

This skill provides organizational-design advice without requesting control over company systems, credentials, or business records.

Use the recommendations as a planning framework and validate the headcount thresholds against your organization's circumstances. If saving observed examples, omit sensitive employee details.

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
  • 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 (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.

md
- Headcount crossed 150 without any structural change or management layer addition
- Founder still coordinating a 200-person company via personal relationships
- "Communication problems" diagnosed as interpersonal without checking if Dunbar limit was crossed
- Org chart flat beyond 50 with no explicit coordination mechanism
- Acquisition integration plan assumes two informal cultures can merge without formal structure

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · examples/ai-native-startup-scaling-2023-2026.md (reported line 13)May include surrounding context.

md
ormal style *matched* its size. Crossing 50 into the 50–150 band, the mechanism must shift to **structured trust** — explicit roles, reporting lines, and lightweight process. Approaching 150, the mismatch becomes acute: informal trust is being asked to coordinate a group that has exceeded the neocortex's capacity to track every relationship. The root cause is **architectural, not interpersonal** — the very trap the skill's Red Flags warn about ("communication problems diagnosed as interpersonal without checking if the Dunbar limit was crossed").

**Step 4 — Prescribe structure.** The right prescription combines two of the skill's three moves. **Formalize** first — replace relationship-based coordination with documented ownership, decision rights, and written process — because this should begin *before* 150, ideally around the 80-person mark per the skill's Pack ("build a management layer before hitting 150"). Then **Layer** — add a management tier so the founders stop being the single