theme-factory
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill repository contains only static theme definitions and instructional text. No scripts, binaries, or automated code execution patterns were detected within the skill files.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve the agent reading and modifying user-provided artifacts (such as slide decks and documents) to apply styling. This creates a surface for indirect prompt injection if the user's files contain malicious instructions.\n
- Ingestion points: User-provided artifacts including slide decks, documents, and HTML landing pages.\n
- Boundary markers: The instructions do not define specific delimiters or security warnings to prevent the agent from following instructions embedded within the processed artifacts.\n
- Capability inventory: The agent is tasked with reading artifact content and applying theme modifications (potentially using file modification tools).\n
- Sanitization: No specific sanitization or validation of the input artifact content is described in the skill instructions.
Audit Metadata