ClawHub
Back to skill

Security audit

Forsy Agent Trace

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently creates local structured records of agent work and includes repeated guidance to avoid saving secrets or sensitive data.

Install this only when you want the agent to create local trace files of its work. Before sharing or publishing generated traces, review them for private prompts, credentials, personal data, proprietary details, internal URLs, logs, and artifact contents, even though the skill tells the agent to redact these.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly directs the agent to save trace.json, manifest.json, and supporting artifacts locally, while the trace schema encourages capturing detailed workflow data such as prompts, memory, tool inputs/outputs, logs, artifacts, and potentially sensitive identifiers. Although the document includes general masking guidance, it does not require an explicit consent gate, safe default redaction, or a warning before persisting potentially sensitive data to disk, which can lead to unintended local data exposure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.