competitor-price-tracker
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as described, using standard tools to fetch web content and send notifications. No suspicious command execution or privilege escalation patterns were found.
- [PROMPT_INJECTION]: The skill processes untrusted data from external URLs, which represents a surface for indirect prompt injection. However, given the specific use-case of price monitoring, this is a known risk factor common to such tools.
- Ingestion points: External product URLs fetched via the
webfetchtool as defined inSKILL.mdandautomation.example.yaml. - Boundary markers: None provided in the instructions to distinguish between trusted instructions and retrieved web content.
- Capability inventory: The skill has access to
webfetch(network read) andemail_send(network write). - Sanitization: There are no explicit sanitization or filtering steps defined for the data extracted from the target pages before it is processed by the agent.
Audit Metadata