ClawHub
Back to skill

Security audit

Essence Distiller

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk text analysis aid that extracts core ideas from user-provided content.

Install this if you want an agent to help distill substantial text into core principles. Review outputs as interpretations, not verified truth, especially for factual, legal, medical, or business decisions.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
### The Discovery Process

1. **I read without judgment** — taking in your content as it is
2. **I look for patterns** — what repeats? What seems to matter?
3. **I test each candidate** — could this be said differently and mean the same thing?
4. **I keep what survives** — the ideas that pass the rephrasing test
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.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The 'When to Use' section lists generic phrases such as 'Simplify this for me' and 'What really matters here?' that overlap with common conversational requests outside this skill's specific domain. The file does not provide exclusion conditions or scope limits to clarify when these phrases should or should not invoke the skill.

Scope Creep

Low
Category
Excessive Agency
Content
I keep both! Your words go in the output (that's your voice), but the normalized version helps find matches across different phrasings.

*(Yes, I use "I" when talking to you, but your principles become universal statements without pronouns — that's the difference between conversation and normalization!)*

**When I skip normalization**: Some principles should stay specific — context-bound rules ("Never ship on Fridays"), exact thresholds ("Deploy at most 3 times per day"), or step-by-step processes. For these, I mark them as "skipped" and use your original words for matching too.
Confidence
65% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.