Back to skill

Security audit

SLA Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only SLA drafting aid with some optional marketing links, but no code, credential access, or hidden execution.

Reasonable to install for SLA drafting and review help. Treat the included benchmark numbers and contract language as starting templates to verify with current business, legal, and vendor context, and be aware that the skill includes optional AfrexAI promotional links.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger condition 'When the user needs SLA help' is broad and underspecified, which can cause the skill to activate in loosely related conversations. Over-broad activation increases the chance of irrelevant instruction injection into unrelated tasks and can unexpectedly expose users to the skill's embedded external promotions.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The suggested trigger phrase "Build an internal SLA between engineering and product" is a natural-language request without any stated invocation constraints, command prefix, or exclusion conditions. In a markdown skill description, this can be interpreted as a broad activation example that overlaps with ordinary business conversation, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill includes promotional links to paid products and unrelated tools that are not necessary to perform the stated SLA-management function. In an agent context, this can bias outputs toward marketing content, create trust-boundary issues, and potentially steer users to external sites without a clear business need.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.