theme-factory
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown documentation and theme configuration files. It does not include any executable scripts, binaries, or command-line operations.
- [INDIRECT_PROMPT_INJECTION]: The skill specifies a workflow for processing user-provided documents, which represents an attack surface for indirect prompt injection if the processed artifacts contain instructions designed to manipulate the agent.
- Ingestion points: User-provided artifacts (slides, docs, reports) and custom theme descriptions in SKILL.md.
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The agent is directed to read internal theme files and apply styling properties to the artifacts.
- Sanitization: The skill relies on the host agent's native safety guardrails without specifying additional sanitization logic.
Audit Metadata