ClawHub
Back to skill

Security audit

Share Of Voice Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent marketing measurement helper that uses public or user-provided data and asks before saving results.

Before installing, expect this skill to read prior marketing memory and user-provided exports, call public/keyless data connectors, and optionally save SOV reports only after you confirm. Review exports for sensitive business data before providing them.

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
Content
## Save Results

After delivering the read, ask: "Save these results for future sessions?" On confirmation, save to `memory/social/share-of-voice-tracker/YYYY-MM-DD-<topic>.md` — see [Skill Contract](../../../references/skill-contract.md) §Save Results Template — and keep the panel record (members, terms, platforms, lock date, break log) current in the same directory. Registry-grade channel facts go only to `memory/events/channels.ndjson` via an authorized `operation: propose` request to `registry-events.py`; [channel-registry](../../../protocol/channel-registry/SKILL.md) is the sole writer of `memory/channels/`. Do not write memory without asking.

## Reference Materials
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.

Static analysis

No suspicious patterns detected.