Back to skill

Security audit

04 Agent Stack Audit

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent automation-audit helper, but it asks the agent to inspect sensitive local operational context without clear scope limits or redaction rules.

Review this carefully before installing. It is not trying to exfiltrate data or install code, but a normal run may inspect local scripts, scheduled tasks, API configuration, installed skills, and memory/context files. Use it only with explicit directory and data-category boundaries, and avoid allowing full secret values or private project context to be copied into generated reports.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:33
Finding

Overbroad Access to Sensitive Operational Context

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manual trigger says to invoke the skill whenever 'the stack feels bloated' or reliability 'has degraded,' which are subjective conditions without clear boundaries. Combined with broad trigger phrases like 'what's still running?', this can cause unintended activation outside a narrowly defined audit context.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
75% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

md
### 1. Crons — Are they alive and earning their keep?

For each launchd agent / cron job / scheduled task:
- Is the process actually running? (check PID, plist/cron status)
- When did it last fire successfully?
- What does it produce? Is that output being consumed by anything?
- Is there a newer/better approach that renders this obsolete?