brand-reader
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from user-specified URLs to generate brand reports. This behavior exposes the agent to indirect prompt injection, where instructions hidden on a website could influence the agent's behavior during the task.
- Ingestion points: External website content (SKILL.md).
- Boundary markers: The prompt lacks specific delimiters or instructions to ignore commands found within the processed website content.
- Capability inventory: The skill is restricted to information extraction and does not use file system or shell tools.
- Sanitization: There is no evidence of filtering or sanitization of the ingested content.
Audit Metadata