Back to skill

Security audit

Viral App

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed viral.app CLI guide that can read and manage account, project, creator, and payout data, with explicit cautions around write actions.

Before installing, verify that you trust the external viral-app CLI and limit VIRAL_API_KEY permissions to the intended organization and tasks. Treat payout initiation or auto-approval as financial actions: review amounts, recipients, campaign IDs, and liability acknowledgements before allowing the agent to run them.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% 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 90)May include surrounding context.

md
- Always call `payouts-calculate` immediately before `payouts-initiate`.
- Pass the returned `calculation` payload and `integrityToken` into `payouts-initiate` unchanged.
- Do not invent or recompute `integrityToken`.
- If using `autoApproveTalentir=true`, also set `acknowledgeFullPayoutLiability=true` and explain the risk before executing.
- Prefer review-first behavior for payout mutations unless the user explicitly asks to initiate or approve payouts.

## Report templates

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 274)May include surrounding context.

md
- `topAccountsBy`
  - `topCreatorsBy`
  - `topEntity`
  - `topListsPerPage`
- Creator Hub creators:
  - `search`
  - `campaigns`

Static analysis

No suspicious patterns detected.