theme-factory

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The 'Create your Own Theme' feature in SKILL.md accepts untrusted user input to generate new styling configurations. This creates a surface where a user could attempt to inject instructions meant to bypass safety filters or influence the agent's behavior during theme application. \n
  • Ingestion points: User-provided inputs used to generate custom themes in SKILL.md. \n
  • Boundary markers: There are no explicit delimiters or specific instructions for the agent to treat the user-provided descriptions as untrusted data or to ignore embedded instructions. \n
  • Capability inventory: The skill is limited to styling artifacts and lacks any internal scripts or tools for network communication or file system modification, mitigating the potential impact of an injection. \n
  • Sanitization: No input validation, escaping, or filtering is defined for the custom theme inputs. \n- [NO_CODE]: The skill package is composed entirely of static Markdown files for documentation and theme definitions. It does not contain any executable code, scripts, or binaries, which significantly reduces the risk of command execution, privilege escalation, or persistence attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:11 AM