qbr-deck
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external files (financial or performance records) using the @file syntax to populate its QBR templates.
- Ingestion points: Performance and financial documents referenced via @file syntax or searched for in the user's directory structure during the 'UPDATE' or 'FIND' modes in SKILL.md.
- Boundary markers: The prompt template lacks explicit delimiters or instructions to ignore potential system-level commands embedded within the data sources it processes.
- Capability inventory: The skill has the ability to generate and save markdown files and invoke the /present tool. It does not possess network exfiltration or shell execution capabilities.
- Sanitization: There are no mechanisms described to sanitize or validate the content of the referenced documents before they are used to generate the final review summary.
Audit Metadata