Back to skill

Security audit

CircleCI

Security checks for vulnerabilities and agentic risk

Overview

The CircleCI workflow is coherent, but its setup fallback runs unverified remote installation code without a separate approval step.

Review and approve CLI installation separately before use, using a verified release where available. Consider the CLI's automatic agent-skill installation and your trust in OOMOL to handle CircleCI credentials and requests. Keep CircleCI permissions limited and retain the documented approval step for pipeline triggers. The bundled instructions were fully reviewed; external installer and service behavior were not verified.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command contains no CircleCI interaction. It executes an installer hosted on an Oomol domain, with no demonstrated connection to the declared CircleCI functionality. This is a materially different capability and accesses an inconsistent resource, rather than an established supporting implementation detail.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
84% confidence
Finding

The only supplied behavior is an authentication command. Authentication could support a CircleCI integration, but this chunk provides no evidence of that connection or of the declared CircleCI functionality. As supplied, its primary behavior differs from the declared purpose.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable HTTPS response directly into Bash executes remote code without a pinned version or independently verified integrity; the PowerShell alternative has the same weakness. Compromise of the installer source or delivery infrastructure could execute attacker-controlled code with the agent's local privileges, potentially exposing files and credentials, although no actual compromise is evidenced here.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

The setup workflow executes downloaded installation scripts without warning the user about running remote code or obtaining approval.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback instructs the agent to install software by executing downloaded scripts without an explicit approval step, expanding a CircleCI task into local code execution. The missing-CLI condition limits exposure, and the declared tool allowlist may block installation if strictly enforced, but neither supplies informed authorization for this host-changing operation.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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 86)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources