signup
Warn
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch and follow an "inbound-routing playbook" from an external GitHub repository (
github.com/coreyhaines31/marketingskills). This allows the agent's logic to be modified by remote content from an unverified source. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit user-supplied signup flows, which serves as an ingestion point for untrusted data. If a user provides a signup flow containing hidden instructions, the agent may follow them during the analysis.
- Ingestion points: User-provided descriptions or code for signup, registration, and account creation flows (SKILL.md).
- Boundary markers: Absent. The instructions do not specify the use of delimiters or clear separation between system instructions and user-provided data.
- Capability inventory: The skill primarily performs text analysis and generates recommendations based on its core principles (SKILL.md).
- Sanitization: Absent. There are no instructions for the agent to filter or escape potentially malicious commands within the audited content.
Audit Metadata