quiz-funnel-expert
Fail
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The file
references/07-saas-pricing-pages.mdcontains multiple links togetmonetizely.com. Automated security scans have flagged this domain as a phishing threat. Providing such links within the skill instructions poses a risk to users who might follow the references for documentation purposes.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by processing untrusted data from the user's current project or funnel description. - Ingestion points: The diagnostic phase described in
SKILL.mdand specialized triggers such as 'Audit an existing onboarding' ingest arbitrary text from the environment. - Boundary markers: The skill lacks delimiters or explicit instructions for the agent to distinguish between legitimate user data and potential embedded commands.
- Capability inventory: The agent has the capability to generate and suggest complex Next.js/Prisma code and business strategies, which could be manipulated by an attacker to include backdoors or misleading logic.
- Sanitization: There is no evidence of filtering or sanitization of external content before it is processed by the agent.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata