Back to skill

Security audit

Buildkite

Security checks for vulnerabilities and agentic risk

Overview

Buildkite changes require approval, but setup can execute unverified code and introduce lasting changes to other agents’ skills.

Review the setup before installing. Use a verified CLI release, understand that Buildkite requests pass through OOMOL, and grant only necessary Buildkite permissions. Control cross-agent skill changes before invoking the CLI; the publisher documents OO_SKILLS_SYNC_DISABLED for disabling startup synchronization. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). The remote installers and deployed backend were not verified; the artifact does not establish credential theft or malicious intent.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 executes an Oomol-hosted installer rather than performing the declared Buildkite operations. Nothing in the supplied code establishes this installer as a supporting dependency for Buildkite. The remote script's contents are not provided, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

md
- `cancel_build` — Cancel a Buildkite build by build number. [destructive]
- `create_build` — Create a new Buildkite build for a pipeline. [write]
- `get_build` — Get a single Buildkite build by organization, pipeline slug, and build number.
- `get_current_access_token` — Inspect the current Buildkite API access token, including scopes and owner summary.
- `get_current_user` — Get the Buildkite user account that owns the current API access token.
- `get_organization` — Get a single Buildkite organization by slug.
- `get_pipeline` — Get a single Buildkite pipeline by organization and pipeline slug.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
- `create_build` — Create a new Buildkite build for a pipeline. [write]
- `get_build` — Get a single Buildkite build by organization, pipeline slug, and build number.
- `get_current_access_token` — Inspect the current Buildkite API access token, including scopes and owner summary.
- `get_current_user` — Get the Buildkite user account that owns the current API access token.
- `get_organization` — Get a single Buildkite organization by slug.
- `get_pipeline` — Get a single Buildkite pipeline by organization and pipeline slug.
- `list_builds_for_organization` — List builds across all pipelines in a Buildkite organization.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The fallback installation command downloads a mutable remote script and immediately executes it without checking a pinned version, signature, or independently trusted digest. Compromise of the installer distribution path could execute arbitrary code with the agent's local privileges, exposing files and credentials; limiting installation to a missing-CLI error reduces frequency but does not remove this risk, and the PowerShell alternative has the same issue.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

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 87)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