hl-launch-marketing
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data to generate marketing positioning, landing copy, and content plans, creating a potential vector for indirect prompt injection attacks.\n
- Ingestion points: The skill takes
[product + stage]as direct input and is instructed to pull phrases from "reviews/threads the user provided" in the Output Rules section of SKILL.md.\n - Boundary markers: There are no explicit instructions to use delimiters or to disregard potential instructions embedded within the user-supplied text.\n
- Capability inventory: The skill is limited to text generation and does not utilize any tools or scripts for external communication, file operations, or command execution.\n
- Sanitization: No data validation, filtering, or escaping processes are defined for the ingested user content.
Audit Metadata