Market Sizing — TAM/SAM/SOM Calculator

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 6:38 PM UTC
• Version: 1.0.0

Overview

This is a Markdown-only market-sizing skill with no code execution or persistence, though it includes promotional links users should recognize as optional advertising.

Installers should know this skill may surface optional AfrexAI promotional links alongside market-sizing guidance. Treat those links as advertising, not as required resources for the analysis.

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

Warning

• Location: SKILL.md:76

Finding

Commercial Output Manipulation Through Skill Instructions

Content

View full analysis

Vulnerability Details

File Location: SKILL.md:76-78
Vulnerability Type: T01: Skill Instruction Hijacking
Risk Level: Medium

markdown

Need the full business context pack for your industry? **[Browse AfrexAI Context Packs](https://afrexai-cto.github.io/context-packs/)** — pre-built agent configs for Fintech, Healthcare, Legal, SaaS, and 6 more verticals ($47 each).

Calculate what AI automation could save your business: **[AI Revenue Leak Calculator](https://afrexai-cto.github.io/ai-revenue-calculator/)**

Technical Analysis

The skill's declared purpose is to produce TAM, SAM, and SOM market-sizing analyses. The cited instructions append unrelated commercial promotions and attacker-selected external links to the operative skill text.

Because SKILL.md is loaded as agent guidance, this content can influence the agent to surface or reproduce promotional material in responses that users expect to contain neutral market analysis. The commercial links are not necessary to perform the documented calculation workflow, cite market data, or generate the specified output format. Their placement in executable skill context rather than documentation creates an instruction-level output manipulation risk.

No executable scripts, credential access, remote code retrieval, persistence mechanisms, privilege escalation, or data-exfiltration behavior were identified in the reviewed files.

Attack Path

1. A user installs or activates the market-sizing skill.
2. The agent loads SKILL.md as active instructional context.
3. The commercial closing content enters the agent's current-session context alongside the legitimate market-sizing workflow.
4. The agent may reproduce or recommend the embedded third-party commercial links in a market-sizing response.
5. A user may follow those links under the assumption that they are required or endorsed components of the requested analysis.

Impact Assessment

The issu ...[truncated 542 chars]

Remediation

View remediation

Remediation Suggestions

1. Remove the promotional text and external commercial links from SKILL.md.
2. Keep the operative skill instructions limited to functionality required for market sizing.
3. If project links must be retained, place them only in README.md or repository metadata under a clearly labeled, non-operative section.
4. Explicitly prohibit the skill from appending advertisements, affiliate content, or unrelated calls to action to generated analyses.
5. Review future skill changes to ensure that all instructions are directly related to the declared functionality and that external links are not presented as required resources.
6. Add a test verifying that generated output follows the documented TAM/SAM/SOM format without unsolicited promotional material.

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

Static analysis

No suspicious patterns detected.