sales-playbook
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (HIGH): The skill is designed to ingest untrusted external data which is then used to drive file-writing capabilities.
- Ingestion points: WebSearch and WebFetch tools are used to gather competitor data and industry benchmarks from external websites.
- Boundary markers: There are no boundary markers or instructions to treat web-fetched content as data only, increasing the risk that the agent follows instructions hidden in HTML or reviews.
- Capability inventory: The skill allows the use of Write and Edit tools, which means an injection could lead to unauthorized file creation or modification.
- Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the web before it is used in the playbook generation process.
Recommendations
- AI detected serious security threats
Audit Metadata