Back to skill

Security audit

onepress-deck

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent deck-building skill whose external OnePress integration and local file output are disclosed and aligned with its purpose.

Install if you want a deck-building workflow. Use local mode for private drafts; connected mode sends prompts and any uploaded documents to OnePress, so avoid confidential material unless you intend to use that service. Keep ONEPRESS_API_KEY in your environment or secret store, not in chat.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

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 84)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 the key. The user can
revoke it anytime in OnePress Settings.

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 223)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 the key. The user can
revoke it anytime in OnePress Settings.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs uploading local files to an external service but does not require explicit user consent or a clear privacy disclosure at the decision point. This creates a real data exfiltration risk because users may provide sensitive documents, logos, drafts, or reports that are then transmitted off-host without an informed opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The quoted user ask begins with "Help me write...", which is a common everyday phrase rather than a narrowly scoped activation cue. In a markdown skill/example file, this can make the intended trigger boundary unclear and increase the chance of unintended or overly broad invocation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example sends the user's full prompt and business context to a third-party service using an API call, but the example text does not clearly warn the user that their content leaves the local environment. This creates a real privacy and data-handling risk because users may assume the skill is local-first and may submit sensitive plans, internal research, or confidential partner materials without informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The recipe explicitly instructs the agent to create and write a file in the user's working directory, which is a local side effect. Even though writing the deck is core to the skill's purpose, the absence of an explicit consent/checkpoint before modifying local files can lead to unexpected filesystem changes, overwriting of similarly named files, or writing into a sensitive working directory context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

These lines direct the agent to fetch generated artifacts and save them locally, which is a file-write operation affecting the user's filesystem. Although the skill generally describes building decks, this specific write behavior is not accompanied here by a confirmation prompt or explicit warning to the user at the point of action.

Content

No source excerpt is available for this finding.