Back to skill

Security audit

onepress-deck-video

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly delegates narrated deck-video rendering to OnePress with user confirmation and disclosed credential handling.

Install only if you are comfortable sending the selected deck, narration plan, and any optional voice sample to OnePress for cloud rendering. Use the browser pairing or a scoped API key, keep ONEPRESS_API_KEY in a secret/env store, and revoke it from OnePress settings if no longer needed.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README makes a security-relevant claim that the skill connects via browser-confirmed pairing without key copying, but the documented installation path actually requires users to manually create and supply a long-lived ONEPRESS_API_KEY. This mismatch can mislead users about the trust model and secret-handling requirements, increasing the chance they expose credentials to the skill or operate under false assumptions about how authentication is performed.

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 75)May include surrounding context.

· {"status":"denied"} · {"status":"expired"} (start over)

text

5. Store `api_key` in the host's secret/env store as `ONEPRESS_API_KEY`. Never
ask the user to paste a key into chat, and never log it. Users can revoke it
anytime in OnePress Settings (or create one manually at
**Settings → Account → API keys**).

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 161)May include surrounding context.

· {"status":"denied"} · {"status":"expired"} (start over)

text

5. Store `api_key` in the host's secret/env store as `ONEPRESS_API_KEY`. Never
ask the user to paste a key into chat, and never log it. Users can revoke it
anytime in OnePress Settings (or create one manually at
**Settings → Account → API keys**).