Back to skill

Security audit

Company Creator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent package generator for agent-company projects, with repo reading and file writing that fit its stated purpose.

Install this if you want help scaffolding Paperclip/Agent Companies packages. Review the generated files before importing them, especially any referenced third-party skills, repo-derived instructions, and optional secret inputs such as GH_TOKEN.

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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises very broad trigger phrases such as 'create a company', 'make me a company', 'create a team of agents', and 'hire some agents', which are common conversational phrases and may match requests outside the intended scope. This can cause unintended invocation of a powerful scaffolding skill that reads repos, proposes file generation, and writes multi-file packages, increasing the chance of misrouting user intent or causing unnecessary file/repo operations.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/companies-spec.md (reported line 100)May include surrounding context.

manager: ../agent-slug/AGENTS.md includes:

  • ../agent-slug/AGENTS.md
  • ../../skills/skill-slug/SKILL.md
text

## PROJECT.md Key Fields

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/example-company.md (reported line 121)May include surrounding context.

md
manager: ../../agents/cto/AGENTS.md
includes:
  - ../../agents/engineer/AGENTS.md
  - ../../skills/code-review/SKILL.md
tags:
  - engineering
---

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/example-company.md (reported line 165)May include surrounding context.

md
manager: ../../agents/cto/AGENTS.md
includes:
  - ../../agents/engineer/AGENTS.md
  - ../../skills/code-review/SKILL.md
tags:
  - engineering
---

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/example-company.md (reported line 175)May include surrounding context.

md
manager: ../../agents/cto/AGENTS.md
includes:
  - ../../agents/engineer/AGENTS.md
  - ../../skills/code-review/SKILL.md
tags:
  - engineering
---

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The instruction activates on 'When a user provides a git repo' and then directs the skill to analyze it and create a company package. This condition is broad and lacks narrowing constraints or exclusion examples, so many ordinary repository-sharing situations could unintentionally invoke the skill.

Content

No source excerpt is available for this finding.