resume-modern
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied messages as a design brief for the
prepare_open_design_brieftool. This creates a surface where an attacker could embed instructions to manipulate the file-authoring process. - Ingestion points: The user message is used as the brief in
SKILL.md. - Boundary markers: There are no delimiters or instructions to prevent the agent from following commands embedded in the user's data.
- Capability inventory: The agent has permissions to call MCP tools and use file-editing tools based on instructions.
- Sanitization: No validation or sanitization of the user input is performed before it is passed to the tool.
Audit Metadata