skills/dacnay816y62-hub/street-photo-illustration-skill/street-photo-illustration/Gen Agent Trust Hub
street-photo-illustration
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, specifically user-uploaded photographs and optional text descriptions, which serves as a potential attack surface.
- Ingestion points: As described in
SKILL.md(Section 2: Source Analysis), the agent analyzes external image content and user-provided directives to generate prompts. - Boundary markers: The instructions do not define explicit delimiters or instructions to disregard potential malicious text embedded within the processed image files.
- Capability inventory: The skill's capabilities are limited to generating and editing images via the agent's built-in tools. It does not have access to the shell, file system, or network operations.
- Sanitization: There is no explicit validation or sanitization logic defined for the user-provided text or image content before it is processed by the AI.
- [NO_CODE]: The skill consists entirely of Markdown and YAML configuration files providing instructions to the AI. It does not include any executable scripts, binaries, or automated installers that could perform unauthorized system actions.
Audit Metadata