The Agent Skills Directory

[SAFE]: No malicious behavior, prompt injections, or security risks were identified. The skill consists of static configuration files and instructional markdown.
[NO_CODE]: The skill does not contain any scripts, binaries, or external dependencies. It leverages the agent's existing file-handling capabilities to perform its tasks.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process external artifacts (e.g., slides, HTML pages) for styling. However, there is no evidence of malicious intent or unsafe logic that would exploit this surface. Evidence: 1. Ingestion points: External document artifacts and user-provided theme descriptions. 2. Boundary markers: No explicit delimiters or warnings provided in the skill files. 3. Capability inventory: File read and write operations required for theme application. 4. Sanitization: No sanitization logic is present within the skill's instructions.

theme-factory