branding-assessment
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface. The skill fetches content from potentially untrusted web surfaces, including personal websites and social media profiles, as part of its diagnostic procedure (Step 2). This external content could contain malicious instructions designed to manipulate the agent's behavior during the comparison or report generation phases.
- Ingestion points: Step 2 fetches data from website home/about pages, GitHub bios/READMEs, Hugging Face profiles, and LinkedIn public profiles.
- Boundary markers: Absent. The skill instructions do not define delimiters or provide specific prompts to the agent to treat the fetched content as untrusted data.
- Capability inventory: The skill utilizes
ReadandWritetools to access local project files and save its findings to the workspace. - Sanitization: Absent. There is no mention of validation, filtering, or sanitization of the content retrieved from external URLs.
Audit Metadata