generating-mock-images
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates user-supplied parameters, such as aspect ratio and subject preferences, into the prompts used by the image generation tool.\n
- Ingestion points: User-provided customization strings for subject matter and aspect ratio selection in SKILL.md.\n
- Boundary markers: Absent; the skill does not explicitly utilize delimiters or instructions to encapsulate or ignore potentially malicious sub-prompts within user input.\n
- Capability inventory: The skill utilizes
generate_imageandask_questiontools and performs file system operations to copy generated images to a public workspace directory.\n - Sanitization: The skill does not specify any validation or sanitization routines for user-provided inputs before they are passed to tools.\n- [SAFE]: The primary functionality of the skill is transparent and aligns with its documented purpose. The use of native tools for image generation and the instruction to avoid custom rendering scripts are positive security practices. No evidence of malicious behavior, exfiltration, or obfuscation was found.
Audit Metadata