theme-factory
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its custom theme generation feature. While no active exploit is present, the logic allows untrusted user input to influence the agent's output and subsequent artifact modification.
- Ingestion points: The 'Create your Own Theme' section in
SKILL.mdinstructs the agent to process user-provided descriptions to generate hex codes and font pairings. - Boundary markers: Absent. There are no delimiters or instructions provided to the agent to ignore potentially malicious commands embedded in the user's theme description.
- Capability inventory: The agent has the capability to modify artifacts (slides, docs, HTML landing pages) as described in
SKILL.mdand the 'Application Process' section. - Sanitization: Absent. The skill does not specify any validation or sanitization for the user-provided theme inputs before they are applied to the artifacts.
Audit Metadata