Back to skill

Security audit

Behind the Scenes & Founder Content

Security checks for vulnerabilities and agentic risk

Overview

This is a social-content drafting skill with clear guardrails and no hidden code, install script, or persistence behavior.

Use this skill for drafting founder or build-in-public content, but review every draft before publishing. Be especially careful with revenue, customer stories, employee matters, health or family details, legal issues, security details, and regulated-industry claims; get consent or compliance review where needed.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 97)May include surrounding context.

md
## House metrics
Comments + DMs + profile visits/follows + saves — the trust signals — via native + `analytics-and-reporting`.
Trust compounds slowly; never judge a BTS post on likes, and never fabricate a number to make the update land.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/behind-the-scenes-2026-reality.md (reported line 53)May include surrounding context.

md
## House metrics
Comments + DMs + profile visits/follows + saves — the trust signals — via native + `analytics-and-reporting`.
Trust compounds slowly; never judge a BTS post on likes, and never fabricate a number to make the update land.

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 75)May include surrounding context.

md
## The transparency tiers (keep this table in mind)
| Share freely | Handle with care (owned choice) | Never |
|---|---|---|
| Process, tools, decisions + reasoning | Revenue/MRR (one-way door) | Customer data / stories without consent |
| Resolved mistakes + lessons | Pricing logic | Team conflicts, personnel, firings |
| Culture-in-action, day-in-the-life | Ongoing struggles (stable footing only) | Active legal/regulatory matters |
| Launch mess, failed drafts, the middle | Personal health/family | Security, credentials, NDA'd material |

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 · evals/evals.json (reported line 78)May include surrounding context.

json
## The transparency tiers (keep this table in mind)
| Share freely | Handle with care (owned choice) | Never |
|---|---|---|
| Process, tools, decisions + reasoning | Revenue/MRR (one-way door) | Customer data / stories without consent |
| Resolved mistakes + lessons | Pricing logic | Team conflicts, personnel, firings |
| Culture-in-action, day-in-the-life | Ongoing struggles (stable footing only) | Active legal/regulatory matters |
| Launch mess, failed drafts, the middle | Personal health/family | Security, credentials, NDA'd material |

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 · references/formats-and-recipes.md (reported line 18)May include surrounding context.

md
## The transparency tiers (keep this table in mind)
| Share freely | Handle with care (owned choice) | Never |
|---|---|---|
| Process, tools, decisions + reasoning | Revenue/MRR (one-way door) | Customer data / stories without consent |
| Resolved mistakes + lessons | Pricing logic | Team conflicts, personnel, firings |
| Culture-in-action, day-in-the-life | Ongoing struggles (stable footing only) | Active legal/regulatory matters |
| Launch mess, failed drafts, the middle | Personal health/family | Security, credentials, NDA'd material |

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 · references/formats-and-recipes.md (reported line 54)May include surrounding context.

md
## The transparency tiers (keep this table in mind)
| Share freely | Handle with care (owned choice) | Never |
|---|---|---|
| Process, tools, decisions + reasoning | Revenue/MRR (one-way door) | Customer data / stories without consent |
| Resolved mistakes + lessons | Pricing logic | Team conflicts, personnel, firings |
| Culture-in-action, day-in-the-life | Ongoing struggles (stable footing only) | Active legal/regulatory matters |
| Launch mess, failed drafts, the middle | Personal health/family | Security, credentials, NDA'd material |