theme-factory
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to style external artifacts such as slide decks, documents, and HTML landing pages, which serve as ingestion points for untrusted data.\n- Ingestion points: Artifacts (slides, docs, reportings, HTML pages) that the agent is instructed to style.\n- Boundary markers: The skill instructions do not provide explicit delimiters or instructions for the agent to distinguish between the artifact's content and potential embedded commands.\n- Capability inventory: The agent is tasked with applying hex codes and font pairings consistently throughout the artifact, which requires it to parse and modify the target content.\n- Sanitization: There are no instructions for the agent to sanitize or ignore instructions embedded within the target artifacts, though a human confirmation step is required for the theme selection itself.
Audit Metadata