ops-growth-analytics
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its use of browser automation and network tracing tools to process external, untrusted data.
- Ingestion points: The skill interacts with external websites and reads network telemetry logs through browser tools and Chrome DevTools MCP (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or guidelines to ignore instructions embedded in the external data being analyzed.
- Capability inventory: The skill utilizes
computer-useandcomputer-automationtools to simulate user journeys and verify interactions (SKILL.md). - Sanitization: There is no mention of sanitizing or validating the content retrieved from web pages or network traces before processing.
Audit Metadata