Back to skill

Security audit

Worksnaps

Security checks for vulnerabilities and agentic risk

Overview

The Worksnaps integration fits its purpose, but setup can execute unreviewed remote code and introduce additional persistent agent skills without clearly explaining these changes.

Review the setup before installing. Use a reviewed, pinned CLI and approve installation separately. Understand that OOMOL mediates access to your Worksnaps account and work records. The publisher documents OO_SKILLS_SYNC_DISABLED=1 for disabling startup skill synchronization; configure that before invoking a compatible CLI if you do not want additional skills installed. External installer contents and hosted connector behavior remain unverified.

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
  • 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
Findings (6)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The code installs software from an Oomol-hosted endpoint rather than accessing Worksnaps. Nothing in the supplied chunk establishes this installation as a supporting dependency for the declared functionality. The remote script's contents are unavailable, so its additional effects cannot be determined.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
86% confidence
Finding

Authentication can be a supporting implementation detail, but the supplied chunk consists entirely of an oo login command with no demonstrated relationship to Worksnaps. Its observable purpose therefore differs from the declared Worksnaps data-access purpose. The command alone does not establish what service is authenticated or how credentials are handled.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable remote installer directly into bash executes its contents with the agent process's privileges without prior inspection or integrity verification. HTTPS and the relevant vendor domain reduce some risks, but a compromised distribution endpoint could still deliver code that accesses local files or credentials; the PowerShell equivalent has the same underlying weakness.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

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

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The setup workflow directs execution of downloaded shell and PowerShell scripts without an explicit approval checkpoint or an explanation of host changes. Although installation is a legitimate prerequisite and only occurs when the CLI is missing, it expands a read-only data request into local code execution.

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 85)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

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

md
## Resources

- Worksnaps homepage: https://www.worksnaps.com
- API documentation: https://api.worksnaps.com/api_docs/