Back to skill

Security audit

Agent Observability Spec

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown guide for designing AI-agent observability, with a real privacy tradeoff around full-content tracing but no hidden execution or installation behavior.

Before installing or using this skill, treat its full-content tracing recommendations as a starting point, not a blanket policy. For production systems, require secret and PII redaction before ingestion, strict access controls, encryption, deletion workflows, and documented limits for incident trace retention.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:37
Finding

Overcollection and Excessive Retention of Sensitive Trace Content

Content
View full analysis
Remediation
View remediation
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