Back to skill

Security audit

Formcarry

Security checks for vulnerabilities and agentic risk

Overview

Formcarry changes require approval, but automatic CLI setup can execute changing remote code and introduce broader, undisclosed agent changes.

Review and install the CLI separately before enabling this skill, including its automatic bundled-skill synchronization. Confirm that OOMOL may access the intended Formcarry account and submissions. Form creation and deletion have clear approval requirements; the unresolved concern is setup and its broader local effects, not evidence of 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
  • 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 (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied code performs remote installer execution, not Formcarry operations. Nothing in the chunk establishes that installing the Oomol CLI is a supporting requirement for Formcarry access. The downloaded script's contents are not supplied, so its further behavior cannot be assessed.

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 without prior inspection, version pinning, or independent integrity verification. HTTPS protects transport but does not prevent a compromised publishing account or distribution service from supplying code that can access local data and credentials; the conditional setup path limits exposure but does not remove this risk.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

Fallback setup executes remote installation scripts without warning about the system-integrity risk.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The fallback instructs installation through immediate execution of downloaded shell or PowerShell scripts without explaining the trust implications or requiring installation-specific approval. Although conditional on the CLI being missing, this can turn a routine Formcarry request into execution of unreviewed code with the invoking 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 78)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