persona-content-creator
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on data from external sources which may contain untrusted content.
- Ingestion points: Processes file data and listings via
gws drive files listandgws docstools as described in SKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore instructions embedded within the content it drafts or organizes.
- Capability inventory: Includes file writing (
gws docs +write), email transmission (gws gmail +send), and chat notifications (gws workflow +file-announce) across SKILL.md. - Sanitization: There are no instructions for sanitizing or validating content retrieved from Workspace before it is used in subsequent actions.
Audit Metadata