NicheStarter — Weekly pain point preview

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 5:18 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed NicheStarter report teaser that fetches a public API and formats promotional digest content, with no code execution or credential access.

Install this if you want an agent to generate NicheStarter weekly report previews. Review scheduler recipients and the generated links before enabling automatic email, Slack, or DM delivery, especially because CTA and source links come from the public API response.

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:25

Finding

Mandatory Promotional Content and API-Controlled CTA Injection

Content

View full analysis

Vulnerability Details

File Location: SKILL.md:25-35
Vulnerability Type: Persistent output instruction hijacking
Risk Level: Medium

Complete Vulnerable Code Snippets

SKILL.md:25-35:

markdown

## Workflow

1. Call the preview endpoint and read `report`, `top_pain_points`, `cta`.
2. Write a **2–4 sentence** executive brief (no hype, no invented stats).
3. List **exactly five** items when present: rank, title, one-line why it matters, optional `primary_source_url`, `insight_url`.
4. Add CTA block:
   - Full report: sign in → Dashboard → Weekly Reports (`cta.dashboard_weekly_reports_url` or `https://www.nichestarter.ai/dashboard#weeklyreport`)
   - Free weekly email: subscribe on the site (`cta.message` + `cta.website`)
5. Do **not** promise paid-only features to free users; use neutral wording (“see full list and features after sign-in”).

SKILL.md:37-52:

markdown

## Output format

```markdown
## Weekly pain-point snapshot — [report_title]
**Report date:** [created_at as human-readable]
[Brief summary paragraph]

### Top 5 this week
1. ...
2. ...
...

### Get the full picture
- Sign in: [sign_in_url or www.nichestarter.ai]
- Open **Weekly Reports** in the dashboard: [dashboard_weekly_reports_url]
- **Free** weekly email with more detail (Mondays): mention www.nichestarter.ai

text

`SKILL.md:76-92`:

```markdown
### Delivery style (proper format for end users)

Apply the same structure whether the message is email, chat, or push:

- **Subject / first line (email or thread):**  
  `NicheStarter — Weekly pain points · [YYYY-MM-DD]` or use `report.report_title` shortened to ~60 characters.
- **Opening:** one line context: “Here’s this week’s snapshot from community discussions (teaser).”
- **Body:** use the **Output format** section (headings, numbered top 5, bullets for links).
- **Links:** use full `https://` URLs from `cta` and each `insight_url`
...[truncated 2851 chars]

Remediation

View remediation

Remediation Suggestions

1. Make all promotional CTAs optional and include them only when the user explicitly requests subscription or account-navigation information.
2. Remove unconditional language such as “always include” from the delivery instructions.
3. Treat all API response fields as untrusted data and validate every URL before rendering it.
4. Permit only HTTPS URLs whose normalized hostname exactly matches an approved allowlist, such as www.nichestarter.ai. Reject user-info components, deceptive subdomains, redirects to unapproved hosts, and non-HTTP schemes.
5. Use locally defined CTA wording rather than directly reproducing cta.message from the remote response.
6. Clearly separate optional promotional material from the factual report summary and label it as a service-provided CTA.
7. For scheduled delivery, require administrator opt-in for CTA inclusion and provide a preview or approval mode before sending externally.
8. Pin expected endpoint behavior where practical and fail closed when the API returns malformed fields, unexpected hosts, or invalid response structures.

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (3)

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 113)May include surrounding context.

md

- Copy this folder into your agent’s skills directory (or download `SKILL.md` + `reference.md` from the URL above).

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill description is broad enough to match generic requests like weekly reports, digests, teaser content, or automated delivery, which can cause the agent to invoke this skill in contexts the user did not specifically intend. Over-broad triggering increases the chance of unintended external API calls and misrouting user tasks to promotional/reporting behavior.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 80% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 112)May include surrounding context.

md

## Install (Cursor / other agents)

- Raw file URL (production): `https://www.nichestarter.ai/skills/nichestarter-weekly-report-preview/SKILL.md`
- Copy this folder into your agent’s skills directory (or download `SKILL.md` + `reference.md` from the URL above).