kai-landing-page
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill automatically explores the user's codebase to ingest information for marketing copy generation, which creates a surface for malicious instructions embedded in project files to influence agent behavior.
- Ingestion points: In Phase 0, the skill reads
MARKETING.md,CLAUDE.md,README.md,PROJECT.md,package.json, and searches for 'email/ad/analytics config' files. - Boundary markers: The skill does not define delimiters or provide specific instructions to the agent to disregard instructions found within the ingested files.
- Capability inventory: The skill is capable of reading various project files and writing output to the
workspace/landing-pages/directory. - Sanitization: There is no evidence of sanitization, filtering, or validation logic applied to the content gathered from the codebase before it is interpolated into the conversion frameworks.
Audit Metadata