phonepe
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external content from phonepe.com which may contain instructions intended to influence the agent's behavior.
- Ingestion points: The
phonepe_com__read_pagetool fetches readable text and links from specified paths or URLs on phonepe.com, which is then processed by the agent. - Boundary markers: The instructions lack explicit delimitation or specific warnings to the agent to disregard or treat as data any instructions found within the retrieved web content.
- Capability inventory: The skill provides capabilities to read pages, browse blog articles, and perform advanced browser-like tasks through the
unbrowsetool suite. - Sanitization: There is no evidence of specific sanitization or filtering of the retrieved web content before it is interpolated into the agent's context.
Audit Metadata