ClawHub
Back to skill

Security audit

Narrative Cascade Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a marketing planning helper whose memory writes are disclosed, limited to its stated purpose, and gated on user confirmation.

Before installing, confirm you are comfortable with the skill reading your narrative canon, claims ledger, baseline maps, and user-provided or scraped owned surfaces. Memory persistence is limited and confirmation-gated, so review any proposed save or registry event before approving 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
  • 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 cascade plan, ask: "Save these results for future sessions?" On confirmation, write `memory/narrative/narrative-cascade-planner/YYYY-MM-DD-<topic>.md` per the [Skill Contract](../../../references/skill-contract.md) §Save Results Template. Referenced-but-unapproved claim wording goes only to `memory/events/claims.ndjson` via an authorized `operation: propose` request to `registry-events.py`; any canon-grade positioning/voice fact that surfaces goes only to `memory/events/narrative.ndjson` via an authorized `operation: propose` request to `registry-events.py` — narrative-registry owns the canon record. Do not write memory without asking.

## Reference Materials

Static analysis

No suspicious patterns detected.