onboarding
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a data ingestion point, taking untrusted user input (name, role, interests, projects) and writing it directly into persistent Markdown files that guide the behavior of other skills in the ecosystem.
- Ingestion points: User responses to open-ended conversational prompts defined in the 'Intelligent Information Extraction' section of
SKILL.md. - Boundary markers: Absent; the user input is directly interpolated into file templates defined in
references/profile-templates.mdandreferences/welcome-guide.md. - Capability inventory: The skill creates a multi-level directory structure and generates several markdown files (
MY-PROFILE.md,MY-INTERESTS.md, etc.) using file-system write operations. - Sanitization: There is no mention of sanitizing, escaping, or validating the user-provided strings before they are persisted to the filesystem.
Audit Metadata