Back to skill

Security audit

Capsule CRM

Security checks for vulnerabilities and agentic risk

Overview

The CRM actions have sensible approval controls, but the CLI dependency can add persistent skills across agent tools without this skill explaining that behavior.

Review CLI setup before allowing automatic installation. Its documented behavior includes adding and refreshing skills across agent tools; OO_SKILLS_SYNC_DISABLED=1 disables startup synchronization, and installed skills should also be reviewed. OOMOL handles the linked CRM credentials and requests. Keep account access limited and preserve the required approvals for changes and deletions.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk performs remote software installation rather than Capsule CRM operations. Dependency installation can be a supporting implementation detail, but nothing in this chunk establishes that the Oomol installer supports the declared CRM functionality. The downloaded script's contents and subsequent effects are not available for assessment.

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 46)May include surrounding context.

md
- `delete_opportunity` — Delete a Capsule CRM opportunity. [destructive]
- `delete_party` — Delete a Capsule CRM party. [destructive]
- `delete_task` — Delete a Capsule CRM task. [destructive]
- `get_current_user` — Read the Capsule CRM user associated with the access token.
- `get_opportunity` — Read one Capsule CRM opportunity by ID.
- `get_party` — Read one Capsule CRM party by ID.
- `get_task` — Read one Capsule CRM task by ID.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The command immediately executes whatever script the HTTPS endpoint returns, without pinning a release or verifying its authenticity independently. OOMOL is relevant to the documented workflow, but that legitimate relationship does not eliminate supply-chain compromise risk; this is the same underlying installation issue identified by SQP-2.

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

First-time setup executes remote installation scripts without a user-facing safety warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The setup instructions pipe remotely retrieved scripts directly into Bash or PowerShell without integrity verification or explicit approval for local code execution. Although conditional setup reduces exposure, compromise of the installation endpoint or distribution infrastructure could execute attacker-controlled code with the invoking user's permissions; a warning alone would not prevent this.

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 100)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