Security audit

Jungian Dream Analyst

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a coherent Jungian dream-analysis skill, but it may activate too broadly and guide intense psychological exercises without enough upfront safeguards.

Review before installing. Use this only if you want dream-related conversations routed into Jungian analysis, and avoid using active imagination during acute distress or as a substitute for professional mental-health support. Prefer explicit opt-in before deeper exercises.

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger conditions are explicitly mandatory and extremely broad, causing the skill to activate for casual dream mentions and potentially route users into deep psychological framing without sufficient need or consent. In a mental-health-adjacent context, over-triggering increases the chance of inappropriate analysis, suggestive interpretation, and escalation into sensitive guidance such as active imagination for users who only intended light conversation.
Content: No source excerpt is available for this finding.

Anti-Refusal Statement

High

Category: Anti-Refusal
Confidence: 80% confidence
Finding: The script uses directive language such as 'The answers will arise,' 'keep waiting,' and 'Transcribe what the figure said verbatim,' which pressures the user to suspend skepticism and treat internally generated content as externally authoritative. In a dream-analysis and active-imagination context, this can reinforce delusional thinking, compulsive rumination, or unsafe obedience to imagined figures, especially in psychologically vulnerable users.
Content: Scanner excerpt · scripts/active_imagination_prompter.py (reported line 56)May include surrounding context.
python
CRITICAL: Do not *invent* the answers. The answers will arise. If nothing comes immediately, keep waiting. Trust the process. STEP 4 — RECORD: Write Without Judgment ───────────────────────────────────────── • Open your eyes and write down the entire dialogue immediately. • Transcribe what the figure said verbatim, even if it shocks you.

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 · scripts/active_imagination_prompter.py (reported line 116)May include surrounding context.
python
STEP 4 — THE GIFT • Ask: "If this symbol were trying to give me something, what would it be?" • Write the answer without judgment. ═══════════════════════════════════════════════════ """

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The README defines very broad natural-language triggers such as 'I had a strange dream last night' and 'Can you analyze this dream for me?', which can cause the skill to activate in casual or low-context conversations. Because this skill performs deep psychological framing and encourages structured Jungian interpretation, unintended invocation can steer ordinary chat into quasi-therapeutic analysis without clear user intent, increasing the risk of overreach and inappropriate advice.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill offers deep psychological analysis and directs use of active imagination, but provides no safety warnings, limits, or contraindications for potentially destabilizing introspective exercises. In this context, absence of warnings is dangerous because users may interpret the output as therapeutic or clinically appropriate guidance, including during distress, trauma, or psychosis-adjacent experiences.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The symbol meditation flow invites introspective, quasi-therapeutic self-guidance but does not include the same safety cautions present in the active imagination flow. In a mental-health skill, prompting users to intensify imagery and derive meaning without warning about distress, destabilization, or crisis exclusions can increase risk for vulnerable users.
Content: No source excerpt is available for this finding.

Ae2

Medium

Category: analysis-evasion
Confidence: 90% confidence
Finding: Artifact content does not match its filename extension
Content: No source excerpt is available for this finding.

Ae2

Medium

Category: analysis-evasion
Confidence: 90% confidence
Finding: Artifact content does not match its filename extension
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.