dojo-david-ogilvy
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implementation consists of educational and instructional markdown content centered on professional advertising frameworks. It does not request access to restricted tools, execute external scripts, or communicate with remote servers.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies user-provided content (e.g., plans or documents for critique) as its primary input for several operating modes. While this presents a surface for indirect prompt injection, the skill does not possess the tools or capabilities required to perform harmful actions on the host system or network if an injection occurred.
- Ingestion points: User-provided situational descriptions and documents intended for review or drafting as outlined in
SKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" warnings for processed user data are present in the instructions.
- Capability inventory: The skill is limited to text generation; it contains no shell execution commands, file modification tools, or network capabilities.
- Sanitization: No explicit sanitization or filtering logic is provided for the processing of external content.
Audit Metadata