kai-content-calendar
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local codebase to generate strategy and content instructions for other skills.
- Ingestion points: Reads files including
MARKETING.md,CLAUDE.md,README.md,PROJECT.md, andpackage.jsonin the project root to discover product context. - Boundary markers: Absent. There are no instructions to delimit ingested content or prevent the agent from following instructions potentially embedded in these files.
- Capability inventory: The skill maintains extensive file-write access to the
workspace/directory and chains into subsequent skills like/kai-writefor batch production. - Sanitization: Absent. Content extracted from the codebase is not validated or sanitized before being interpolated into content briefs and drafts.
Audit Metadata