ClawHub
Back to skill

Security audit

Attribution Reconciler

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed marketing attribution workbook that uses user-provided exports and only saves persistent results after asking.

Before installing, be aware that this skill may process order IDs, conversion exports, spend data, and attribution results. Only provide exports you are comfortable using for reconciliation, and only approve the memory save step if you want those summarized results persisted for future sessions.

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 82)May include surrounding context.

md
## Save Results

After delivering, ask "Save these results for future sessions?" If yes, write the workbook to `memory/ad/attribution-reconciler/YYYY-MM-DD-<topic>.md`: the match table, de-duped counts, normalized-window/currency view, model-comparison table, incrementality read (or N/A), and the handoff summary. Promote the de-duped count, double-count rate, and incrementality result to `memory/hot-cache.md`. Push unresolved order/claim mismatches to `memory/open-loops.md`. Do not write memory without asking. `memory-management` later rolls these standing workbooks into the monthly aggregate.

## Reference Materials