suede-onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process local context files, which represents a potential indirect prompt injection surface.
- Ingestion points: SKILL.md directs the agent to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md.
- Boundary markers: The instructions lack explicit delimiters to isolate external context from the agent's core instructions.
- Capability inventory: No scripts with tool capabilities (like file writing or network access) are included in the skill package itself.
- Sanitization: The skill does not provide mechanisms for validating or sanitizing the content of the external files before they are processed by the agent.
Audit Metadata