ClawHub
Back to skill

Security audit

Content Reviewer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped influencer-content review aid that reads campaign evidence, produces review feedback, and only writes an audit artifact after user permission.

Before installing, be aware that this skill can influence approval or revision recommendations for influencer content, and in a full repository/plugin setup it may run local scoring/validation scripts. Review its audit output before acting on business or payment decisions.

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
80% 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 103)May include surrounding context.

md
## Persistence

Ask before writing. On approval, validate the complete v3 draft with `validate-audit-artifact.py` against the intended `memory/audits/influencer/YYYY-MM-DD-<topic>.md` relative path, persist only through one full-content Write, and revalidate the target per the auditor runbook. Edit/shell/MCP mutations of the reserved sink are unsupported. Do not autonomously modify claims, contracts, registry records, candidates, or hot cache.

## Reference Materials

Static analysis

No suspicious patterns detected.