ClawHub
Back to skill

Security audit

OKRs

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only OKR guidance skill with no executable code or unusual authority requests.

This skill appears safe to install for OKR writing and review. It may recommend related skills, but those installs are explicitly conditioned on user confirmation, so review any additional skill before installing it.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

md
- Avoid the circular KR: O "grow revenue" with KR "increase revenue 20%" restates the O. The KR must be a driver you believe moves the O (pipeline, win rate, expansion), not the O itself measured.
- One named owner per KR, not per O. Unowned KR = no one acts. The O owner coordinates; they do not own every KR.
- Measurability test: if the data pipeline cannot produce the number on a weekly cadence, pick a proxy you can measure or drop the KR. A number you read only at quarter-end is a postmortem, not a steering wheel.
- Guardrail KRs: 1-2 per set, metrics you must not break while pursuing the O (NPS > 40, error rate < 0.5%, margin held). Without guardrails, teams hit the O by breaking something expensive off-book.
- Stretch check: a KR you are 100% sure you will hit is a commitment, not a KR. A real KR carries genuine uncertainty about reaching 1.0.
- Confidence per KR: owner sets a 0-1 confidence at the weekly check-in and updates it. Trend beats level; falling confidence two weeks running = intervene now, do not wait for the score.

Static analysis

No suspicious patterns detected.