theme-factory
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features a custom theme generator that processes user-provided descriptions to create new styling palettes. This represents an indirect prompt injection surface where external data is ingested into the agent's context.
- Ingestion points: User-provided descriptions in the 'Create your Own Theme' workflow described in
SKILL.md. - Boundary markers: Absent; there are no specific delimiters or instructions for the agent to ignore potentially malicious commands embedded in user-supplied theme descriptions.
- Capability inventory: The skill instructs the agent to apply styling (colors and fonts) to artifacts like documents and slide decks.
- Sanitization: Absent; the skill does not define validation or filtering logic for the user-provided content before processing it for theme generation.
- [NO_CODE]: The skill package is composed entirely of markdown instructions, configuration metadata for themes, and a standard license text. It does not include any scripts (e.g., Python, JavaScript, Shell), binaries, or automated installation manifests, which significantly minimizes the potential for malicious execution or system exploitation.
Audit Metadata