project-illustrator
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary operations involve reading repository documentation, analyzing existing branding, and generating images using standard tools. These actions are consistent with the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a vulnerability surface by ingesting untrusted content from the target repository's documentation and README files.
- Ingestion points: The skill explicitly instructs the agent to read the repository's README, product copy, and documentation files to learn about the project's identity (SKILL.md, Section 1).
- Boundary markers: There are no instructions to use delimiters or ignore potentially malicious instructions embedded within the ingested project files.
- Capability inventory: The agent has the capability to write files to the repository (SKILL.md, Section 6) and invoke external image generation tools (SKILL.md, Section 4).
- Sanitization: The skill does not prescribe any sanitization, validation, or filtering of the text content extracted from the repository before it is used to influence the generation process.
Audit Metadata