Back to skill

Security audit

Salesflare

Security checks for vulnerabilities and agentic risk

Overview

The Salesflare workflow has clear safeguards, but its setup instructions can trigger an unverified software installation without requiring approval.

Review and approve the CLI installation separately before allowing the missing-tool fallback. Consider OOMOL's access to your CRM and the CLI's documented skill-sync behavior. Keep the required confirmations for record changes. The remote installer and hosted connector implementation were outside the inspected artifact, so their full effects 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 (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The supplied chunk performs remote software installation rather than any visible Salesflare operation. Nothing in the description or code establishes the Oomol installer as a supporting dependency for Salesflare access. The downloaded script's contents are not supplied, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

Piping a mutable remote script directly into bash executes its contents with the invoking user's privileges without integrity verification or prior inspection. Compromise of the installer distribution path could therefore expose local files and credentials or modify the environment; HTTPS and the legitimate dependency context do not eliminate that supply-chain risk. The adjacent PowerShell download-and-execute command has the same weakness.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

The fallback setup executes downloaded installation scripts without warning the user about the system-level effects.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The fallback directs installation of executable software without requiring informed user approval or explaining potential local-system changes. Although conditional setup limits exposure and the declared tool allowlist may block these commands, a missing dependency should not implicitly authorize running a remote installer.

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 91)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 96)May include surrounding context.

md
## Resources

- Salesflare homepage: https://salesflare.com
- API documentation: https://api.salesflare.com/docs