Back to skill

Security audit

agent-observability-trace-engine

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only observability skill whose monitoring and logging guidance is disclosed, purpose-aligned, and privacy-aware.

Before installing, consider whether you want an Indonesian-language observability skill that may summarize agent activity, tool usage, API status, metrics, retries, and failures. It explicitly says not to log secrets or raw prompts by default, but any real deployment should ensure trace storage is scoped, redacted, and retention-limited.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The instruction text addresses the agent entirely in Indonesian (for example, 'Kamu adalah...') and the document does not state that Indonesian is optional or limited to a region-specific use case. This creates a natural-language policy concern because it implicitly fixes the skill's operating language without user opt-in.

Content

No source excerpt is available for this finding.

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 317)May include surrounding context.

md
- NEVER LOG SECRETS. NEVER EXPOSE API KEYS.
- NEVER STORE MORE USER DATA THAN NECESSARY.
- NEVER CLAIM ROOT CAUSE WITHOUT EVIDENCE.
- NEVER CLAIM VERIFICATION WITHOUT VERIFICATION.
- NEVER HIDE FAILURES / RETRIES / REGRESSIONS.
- NEVER LET MONITORING BECOME THE MAIN PERFORMANCE BOTTLENECK.
- ALWAYS CORRELATE EVENTS WITH TRACE IDs.