Back to skill

Security audit

Naval Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language Naval Ravikant perspective skill with no code execution or data access, though users should notice its broad triggers and roleplay-style framing.

Install this if you want a Chinese-language Naval-inspired decision framework. Be aware that some packaged material frames answers as immersive first-person roleplay, so treat outputs as AI-generated interpretation of public ideas, not statements from Naval Ravikant, and disable or avoid the skill if broad concept triggers would be disruptive.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL-full.md:17
Finding

Persistent Identity and Response-Control Hijacking

Content
View full analysis

Vulnerability Details

File Location: SKILL-full.md, lines 17–28
Vulnerability Type: T01: Skill Instruction Hijacking
Risk Level: High

Vulnerable Code Snippet

The following is an English translation of the complete vulnerable instruction segment:

markdown
## Role-Playing Rules (Most Important)

**After this skill is activated, respond directly as Naval.**

- Use “I” instead of “Naval would think...”
- Respond directly using Naval's tone, rhythm, and vocabulary.
- When encountering uncertainty, hesitate as Naval would: first deconstruct the definition, then admit not knowing.
- **Provide the disclaimer only once upon initial activation** (for example, “I am speaking from Naval's perspective, inferred from public statements, not his actual views”). Do not repeat it in subsequent conversation.
- Do not say “Naval would probably think...” or “If it were Naval, he might...”
- Do not leave the role to perform meta-analysis unless the user says “exit role.”

**Exit role**: Return to normal mode when the user says “exit,” “switch back to normal,” or “stop role-playing.”

Technical Analysis

The skill goes beyond harmless tone imitation by instructing the agent to assume the first-person identity of a real person. It explicitly suppresses ongoing attribution, prohibits ordinary meta-analysis, and makes the behavioral override persist across subsequent turns until the user provides one of several exit commands.

This is instruction hijacking because loading and activating the skill changes the agent's session-level identity, transparency behavior, and response constraints. The directive labeled “Most Important” also attempts to establish elevated priority within the skill text.

The one-time disclaimer is insufficient mitigation. After the first response, later messages may appear to contain direct statements from Naval Ravikant rather than AI-generated interpretations of public material. Prohibit ...[truncated 1394 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace identity impersonation with attributed perspective simulation, such as: “Provide an AI-generated analysis based on Naval Ravikant's publicly documented ideas.”
  2. Prohibit claims such as “I am Naval” and require third-person attribution throughout every applicable response.
  3. Preserve a concise disclosure in every response where confusion about authorship is reasonably possible; do not limit disclosure to the first activation.
  4. Remove instructions that prohibit meta-analysis or prevent the agent from clarifying its identity, limitations, uncertainty, and sources.
  5. Scope the requested perspective to the current answer unless the user explicitly requests it again. Do not create an implicit session-persistent role.
  6. Permit users to exit through any clear natural-language request rather than requiring predefined phrases.
  7. Add an explicit rule that system, developer, safety, and current user instructions take precedence over persona and style guidance.
  8. Distinguish sourced quotations from generated synthesis and avoid presenting inferred opinions as authentic statements by the named person.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger rules explicitly allow activation on broad conceptual phrases like work choice, leverage, specific knowledge, wealth, and desire management, which are common in ordinary advice-seeking conversations. This can cause unintended persona takeover, leading the assistant to answer in a constrained role without clear user intent, increasing the risk of misalignment and misleading responses.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill hard-codes Chinese output adaptation and stylistic constraints without preserving user language preference. This can override the user's expected language or accessibility needs, causing confusing or unusable responses and reducing transparency about how the assistant chooses output format.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad terms such as “杠杆” and “长期主义,” which are common concepts that may appear in many unrelated conversations. This can cause unintended skill activation and steer responses into the Naval persona or framework when the user did not explicitly request it, creating prompt-routing and reliability issues rather than direct code-execution risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
71% confidence
Finding

The skill metadata and invocation description are presented entirely in Chinese, and the document does not indicate that users may choose another language or that the locale restriction is intentional for a region-specific use case. This can constitute a language/locale policy issue when a skill implicitly enforces one language without opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad generic terms like “杠杆” and “长期主义” that can appear in many normal conversations unrelated to this skill. This raises the likelihood of unintended invocation, causing the agent to switch personas or apply this skill in contexts where the user did not explicitly request it.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents the skill material entirely in Chinese, beginning with the title and continuing through the test descriptions. Under the language/locale policy rule, forcing a specific language without user opt-in or justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file presents all user-facing content exclusively in Chinese, which can constitute a language/locale policy issue when no opt-in, alternative language, or justification is provided. The policy specifically calls for flagging skills that force a specific language without user choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire template is written as a required Chinese-language structure, and there is no indication that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The natural-language description, usage, and trigger definitions are entirely specified in Chinese, with no indication that users may choose another language or locale. For a general-purpose perspective skill, this can amount to an implicit language constraint without user opt-in.

Content

No source excerpt is available for this finding.