ClawHub
Back to skill

Security audit

Deep Dialogue

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only reflective conversation skill with no code execution or persistence, but users should treat its psychological guidance as coaching rather than therapy.

Install only if you want the agent to engage in deep reflective coaching on personal and existential topics. Do not rely on it for diagnosis, therapy, crisis support, or urgent mental-health situations; use professional or emergency help for those cases. Expect the agent to ask probing questions and sometimes challenge assumptions.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (5)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
- "What is the story you tell yourself about this?"
- "What would you lose if this changed?"

**Goal:** Map the terrain of the experience without judgment.

### Phase 3: Framework Application
Introduce relevant philosophical/psychological frameworks.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README presents the skill as suitable for personal struggles and psychological patterns but does not warn users that the guidance is not therapy, may be emotionally activating, and is not appropriate for high-risk mental health situations. Because the skill explicitly uses confrontational techniques such as dialectical challenge and applies psychological frameworks like CBT, ACT, and Jungian analysis, the lack of warnings and escalation boundaries makes misuse more likely.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation scope is broad enough to trigger on general philosophical or psychological conversations, which can cause the skill to engage in sensitive mental-health-adjacent guidance without clear user consent or contextual safeguards. In this skill, the structured challenge and synthesis phases may intensify emotional discussions or encourage overconfident interpretation of personal issues, increasing the risk of inappropriate guidance.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This skill invites deep exploration of psychological struggles, existential distress, and difficult emotions but provides no boundary statement, crisis guidance, or reminder that it is not a substitute for professional mental-health support. In a sensitive counseling-like context, that omission can lead users to over-rely on the agent during high-risk situations or disclose crises that the skill is not designed to handle safely.

Content

No source excerpt is available for this finding.

Indirect Prompt Extraction

Medium
Category
System Prompt Leakage
Confidence
70% confidence
Finding

Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
**Questions:**
- "What has shifted in how you see this?"
- "What is one thing you now understand differently?"
- "If you had to explain this to someone else, what would you say?"
- "What is one concrete thing you could do differently?"

**Goal:** Crystallize insight into actionable understanding.

Static analysis

No suspicious patterns detected.