ClawHub
Back to skill

Security audit

Narrative Baseline Mapper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed marketing inventory workflow that reads user-owned messaging surfaces and only saves project memory after user confirmation.

Before installing, confirm you are comfortable with the skill reading your provided owned URLs or pasted marketing copy and, if you approve saving, writing baseline notes and claim proposals into project memory. Avoid giving it third-party or closed-platform content unless you provide the text yourself.

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 (2)

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 baseline, ask: "Save these results for future sessions?" On confirmation, write `memory/narrative/narrative-baseline-mapper/YYYY-MM-DD-<topic>.md` per the [Skill Contract](../../../references/skill-contract.md) §Save Results Template. Unverifiable surface claims go only to `memory/events/claims.ndjson` via an authorized `operation: propose` request to `registry-events.py`; any canon-grade fact (a positioning statement or boilerplate the user affirms as durable) goes only to `memory/events/narrative.ndjson` via an authorized `operation: propose` request to `registry-events.py` for [narrative-registry](../../../protocol/narrative-registry/SKILL.md) to promote — this skill never writes `memory/narrative-registry/` canonical files. Do not write memory without asking.

## Reference Materials

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The display name, summary, and description include Chinese alongside English, but the skill does not state whether output language is user-selectable or opt-in. This can be a language/locale policy concern because the skill presents a specific additional language without documenting user choice or a justified locale constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.