genmedia-image-artist
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains explicit instructions to circumvent safety filters.
- Evidence: The "Technical Tips" section in
SKILL.mdinstructs the agent: "If a generation fails due to safety filters, perform a 'clinical rewrite' of the prompt to remove emotionally charged labels while keeping the physical description." - [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing untrusted user input without sufficient safeguards.
- Ingestion points: User-provided text descriptions for image generation in
SKILL.mdworkflows. - Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions embedded within user prompts.
- Capability inventory: Access to the
mcp_nanobanana_nanobanana_image_generationtool. - Sanitization: Absent; there are no instructions to validate or filter user-supplied content before passing it to the generation tool.
Audit Metadata