ClawHub
Back to skill

Security audit

Strategic Narrative Designer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused marketing narrative helper that reads and writes scoped project memory only with disclosed confirmation and proposal flows.

Before installing, expect this skill to read relevant project memory and, if you approve saving, write narrative outputs and proposal events. Review generated proof claims before promoting them into canonical messaging or claims records.

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
  • 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
Findings (1)

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 68)May include surrounding context.

md
## Save Results

After delivering the arc, ask: "Save these results for future sessions?" On confirmation, save to `memory/narrative/strategic-narrative-designer/YYYY-MM-DD-<topic>.md` — see [skill-contract.md](../../../references/skill-contract.md) §Save Results Template. Every `[needs source]` proof beat goes only to `memory/events/claims.ndjson` via an authorized `operation: propose` request to `registry-events.py`; a stable, canon-grade arc goes only to `memory/events/narrative.ndjson` via an authorized `operation: propose` request to `registry-events.py` — never write `memory/narrative-registry/` canonical files directly, only [narrative-registry](../../../protocol/narrative-registry/SKILL.md) promotes those. Do not write memory without asking.

## Reference Materials

Static analysis

No suspicious patterns detected.