Back to skill

Security audit

Sentry

Security checks for vulnerabilities and agentic risk

Overview

The Sentry workflow is coherent, but its automatic setup can execute changing remote code without a separate approval or integrity check.

Review and approve CLI installation separately before using this skill, preferably with a fixed, verified release. Check its bundled-skill installation behavior and grant only the Sentry access needed. Sentry requests pass through OOMOL, and the remote installers' exact behavior could not be verified in this review.

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
98% confidence
Finding

The supplied code performs no visible Sentry operations. Its sole action is downloading and executing an Oomol installer, which is materially different from the declared Sentry functionality. Nothing in the supplied chunk establishes this installer as a supporting Sentry dependency. The downloaded script's contents and further effects cannot be determined from this chunk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
83% confidence
Finding

The supplied chunk only invokes a login command and provides no connection between oo and Sentry. Authentication could be a supporting implementation detail if that connection were established, but the supplied content does not establish it or demonstrate the declared Sentry functionality.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The curl-to-bash command immediately executes whatever the installation endpoint returns, with no pinned version or independent integrity verification. Compromise of the endpoint or its delivery infrastructure could therefore execute arbitrary code with the user's permissions; HTTPS alone does not protect against a compromised publisher.

Content

Scanner excerpt · SKILL.md (reported line 73)May include surrounding context.

The setup workflow executes downloaded installer scripts without warning about remote code execution or local system changes.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The fallback setup instructs the agent to execute downloaded shell or PowerShell code without an explicit installation approval step, artifact verification, or review. Although triggered only when the CLI is missing, this expands a Sentry task into local code execution and system changes under the executing user's privileges.

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 94)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