ClawHub
Back to skill

Security audit

First Principles Thinking

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only reasoning skill that adds structured analysis prompts without code execution, credentials, persistence, or hidden data movement.

Install this if you want the agent to slow down and structure complex decisions, debugging, architecture, and brainstorming around assumptions and verification. Expect more analysis on broad prompts; use the documented skip phrases when you want direct implementation.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 28)May include surrounding context.

md
Do NOT propose a solution, recommend a technology, or start writing code until:

1. The problem has been restated in terms of outcomes (not solutions). If the
   user already provided enough context, proceed without asking for confirmation;
   otherwise ask one targeted clarifying question or state the working assumption.
2. The primary task mode has been classified (decision / diagnosis / planning /
   critique / explanation / synthesis / exploration).

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The auto-trigger section activates on generic phrases like "design," "slow," "brainstorm," "creative," and "from scratch," which commonly appear in ordinary conversations and many unrelated tasks. Although skip signals are provided, the trigger scope remains broad enough that the skill could activate unintentionally outside a clearly narrow context.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 326)May include surrounding context.

md
`[CLAIM]`, `[ASSUMPTION]`, `[CONSTRAINT]`, or `[UNKNOWN]` instead. User-
supplied statements start life as `[CLAIM]`; they are promoted to `[TRUTH]`
only after the test passes, or downgraded to `[ASSUMPTION]` if the belief is
being used without verification.

**Assumption Ledger v2** -- classify each `[ASSUMPTION]` and record its risk profile:

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 814)May include surrounding context.

md
- [ ] Problem stated as an outcome, not a solution
- [ ] Primary mode (and secondary, if any) classified and announced
- [ ] Depth level announced, or working assumptions stated if proceeding without confirmation
- [ ] Tool Plan selected only the reasoning tools warranted by the problem
- [ ] Claim Ledger populated across all five lanes (truths, claims, assumptions, constraints, unknowns)
- [ ] Mechanism Map created when causality, strategy, systems, or debugging matter

Static analysis

No suspicious patterns detected.