ClawHub
Back to skill

Security audit

Advocacy Program Designer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed planning assistant for employee advocacy programs, with limited memory writes and explicit guardrails against automated posting or engagement.

Before installing, be aware that this skill is intended to work with employee handles, disclosure lines, opt-in evidence, and internal content plans. That is appropriate for its purpose, but users should only provide roster data they are allowed to use and should review any proposed memory or registry changes before confirming them.

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 69)May include surrounding context.

md
## Save Results

After delivering the blueprint, ask: "Save these results for future sessions?" On confirmation, save to `memory/social/advocacy-program-designer/YYYY-MM-DD-<topic>.md` — see [Skill Contract](../../../references/skill-contract.md) §Save Results Template. Advocate rows, cadence commitments, and other registry-grade facts go only to `memory/events/channels.ndjson` via an authorized `operation: propose` request to `registry-events.py` — never directly into `advocate-roster.md` or any other `memory/channels/` file. Do not write memory without asking.

## Reference Materials

Static analysis

No suspicious patterns detected.