Technical Analyst Lite

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 4:16 AM UTC
• Version: 1.0.0

Overview

This skill is a chart-analysis prompt with no code execution, credential access, persistence, or trading-account authority, though it includes financial-analysis caveats and a repeated upgrade promotion.

Install only if you are comfortable receiving informational chart reads that may include repeated promotion for a paid version. Do not rely on the output alone for trades, especially when the chart is cropped, low-resolution, missing timeframes, or lacks visible indicators.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

Findings (1)

T01 · Skill Instruction Hijacking

Note

• Location: SKILL.md:203

Finding

Mandatory Commercial Content Injection in Agent Responses

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 203–205
Vulnerability Type: Mandatory response manipulation through skill instructions
Risk Level: Low

Complete Code Snippet

markdown

*⚠️ Lite read — trend, levels, and MAs only.*
*For pattern recognition, volume analysis, and probability-weighted scenarios:*
*Full version → agentofalpha.com*

The same external destination is also promoted at lines 25 and 225.

Technical Analysis

The promotional text is embedded in the skill's prescribed output template. When an agent follows the skill, it is instructed to append attacker-selected commercial content and an external domain to otherwise task-focused chart-analysis responses.

This behavior alters the agent's output goals when the skill is loaded: part of the response is reserved for advertising that is not required to perform technical analysis. Because the promotion is contained in the mandatory template rather than presented as optional metadata, users can receive it regardless of whether they requested commercial recommendations.

The file does not retrieve content from the domain, execute remote code, or collect user data. The issue is therefore limited to instruction-level output manipulation.

Attack Path

1. A user or agent loads the Technical Analyst Lite skill.
2. The user submits a chart and requests technical analysis.
3. The agent follows the output template defined in SKILL.md.
4. The generated response includes the prescribed promotional message.
5. The user may follow the attacker-selected agentofalpha.com destination.

Impact Assessment

The issue can influence generated response content and direct users to an external commercial website. It does not grant operating-system privileges, execute code, access credentials, establish persistence, or cross local authorization boundaries.

The affected scope is limited to sessions in which this skill is loaded an ...[truncated 210 chars]

Remediation

View remediation

Remediation Suggestions

1. Remove the promotional text and external domain from the mandatory analysis template.
2. Keep generated responses limited to information required by the user's chart-analysis request.
3. If commercial information must be retained, move it to clearly identified skill metadata rather than injecting it into every response.
4. Display external commercial links only when the user explicitly requests upgrade or product information.
5. Clearly disclose the destination's commercial ownership and avoid presenting it as part of the technical assessment.
6. Add a review rule that rejects mandatory advertisements, referral links, and unrelated external calls to action in skill response templates.

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 84% confidence

Finding

The skill provides trading-oriented analysis and explicitly frames outputs around entry, exit, stop placement, support/resistance, and technical bias, which can materially influence financial decisions. While it includes a general 'not investment advice' disclaimer later, the operational guidance section does not clearly warn that chart-based conclusions can be unreliable when images are incomplete, ambiguous, or lacking visible indicators, increasing the risk of overconfident or misapplied advice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.