about-me-avatar
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data from the
{ABOUT_ME}profile and interpolates it directly into the prompt template sent to theimage_gentool. - Ingestion points: The
{ABOUT_ME}variable inSKILL.mdis populated with user-provided content. - Boundary markers: No delimiters (such as XML tags or explicit block quotes) or "ignore embedded instructions" warnings are used to separate the system's instructions from the user-provided data in the final prompt.
- Capability inventory: The skill uses the
image_gentool to generate and overwrite image files. - Sanitization: No evidence of sanitization, escaping, or validation of the
{ABOUT_ME}content is present before it is interpolated into the prompt.
Audit Metadata