Back to skill

Security audit

Energy Market Intelligence

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Alberta energy market briefing aid that uses public sources and includes clear limits against trading, price, regulatory, and PPA recommendations.

Install only if you want an agent to produce Alberta electricity-market analysis from public AESO, AUC, and regulatory sources. Treat outputs as analytical briefings, not financial, trading, procurement, legal, or compliance advice, and verify current market data before acting.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README advertises very broad trigger phrases such as asking for an 'Alberta energy market briefing' or 'energy market update,' which can overlap with ordinary user requests and cause the skill to activate in contexts where the user did not explicitly intend to invoke this specialized behavior. That increases the chance of prompt/skill overreach, where the agent may inject domain-specific framing, recommended actions, or sourcing workflows into otherwise general conversations.

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 194)May include surrounding context.

md
- Current AESO connection project list for queue and capacity pipeline
   - Alberta government gazette for enacted carbon pricing or regulatory changes

5. Frame the analysis: historical data provides useful baseline context for structural trends and seasonal patterns, but should not be used for current position-sizing, procurement timing, or cost forecasting without verification against current conditions.

## Regulatory change handling