Back to skill

Security audit

Crunchbase

Security checks for vulnerabilities and agentic risk

Overview

The Crunchbase workflow fits its purpose, but setup can execute unverified remote code and introduce broader agent changes without clearly scoped approval.

Review and approve CLI installation separately before allowing the agent to use this skill. Verify the installer and release, check automatic agent-skill synchronization, and connect only the intended Crunchbase account. Installer contents and delivered runtime behavior were not verified; no credential theft or malicious intent was established.

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
96% confidence
Finding

The supplied chunk performs remote software installation rather than Crunchbase data retrieval. Although installation can be a supporting implementation detail, this chunk provides no evidence connecting the Oomol installer to the declared Crunchbase functionality. The downloaded script's contents and further effects are not available for assessment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

The supplied chunk performs only authentication; it contains no Crunchbase search or read operation and establishes no relationship between oo and Crunchbase. Authentication could be a supporting implementation detail, but that connection is not demonstrated here. The command alone does not establish credential theft or other malicious behavior.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
99% confidence
Finding

The command pipes a mutable remote script directly into Bash without version pinning or independent integrity verification; the PowerShell alternative has the same weakness. If the installer source or delivery infrastructure is compromised, executing it could run attacker-controlled code with the agent process's permissions, exposing local files and credentials.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Fallback setup executes remotely downloaded installers without warning the user about system changes.

Medium
Category
Output Handling
Confidence
95% confidence
Finding

The fallback directs installation of executable software without first explaining the system changes or obtaining explicit installation approval. A missing prerequisite for a read-only data request should not implicitly authorize host modification; the failure-only condition limits exposure but does not establish user consent.

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 82)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 87)May include surrounding context.

md
## Resources

- Crunchbase homepage: https://www.crunchbase.com
- API documentation: https://data.crunchbase.com/docs/using-the-api