ClawHub
Back to skill

Security audit

Audience Belief Mapper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed marketing research helper that maps user-provided buyer notes into belief, objection, and switching-force summaries, with controlled optional memory saving.

Before installing, consider that this skill is intended to work with customer interviews, sales notes, support tickets, and local memory files. Use it only where saving those summaries to memory is acceptable, and review any proposed claim or narrative records before allowing them to persist.

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 map, ask: "Save these results for future sessions?" On confirmation, save to `memory/narrative/audience-belief-mapper/YYYY-MM-DD-<topic>.md` per the [Skill Contract](../../../references/skill-contract.md) §Save Results Template. Unverified quote/claim wording goes only to `memory/events/claims.ndjson` via an authorized `operation: propose` request to `registry-events.py`; a durable canon-grade belief or reframe goes only to `memory/events/narrative.ndjson` via an authorized `operation: propose` request to `registry-events.py` — never to `memory/narrative-registry/` canon files directly. Do not write memory without asking.

## Reference Materials

Static analysis

No suspicious patterns detected.