Back to skill

Security audit

Draco Competitor Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only competitor analysis writing aid with no executable behavior or hidden data access.

Installers should understand that this skill may influence the structure and style of business analysis outputs, but it is transparent Markdown guidance and does not add executable code, data access, or persistence.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

md
Always push past description. Ask: **what was the main contradiction / main variable?**

## Output rule

Every competitor-analysis section must end with three explicit buckets:
- **What to borrow**

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/marketing.md (reported line 7)May include surrounding context.

md
## Core principle

Do not judge a campaign by creativity alone. Judge it by whether the background, objective, strategy, creative expression, execution, and result fit together.

## Six-part framework

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The instruction 'Use when the task is to analyze repositioning, rebranding, young-ification, premiumization, or diversification' describes a wide class of common business-analysis tasks without defining specific invocation phrases, exclusions, or scope boundaries. This ambiguity could cause the skill to be selected for general branding discussions that are not actually 'brand upgrade competitor analysis.'

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.