invoice-chaser
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill functions as a structured prompt for text generation.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided invoice details (such as client names and amounts) to populate its email drafting template. This creates a data ingestion surface; however, the skill lacks access to dangerous capabilities like file system modifications, network requests, or shell execution. The resulting output is a text draft intended for user review, which mitigates the risk of automated exploitation.
Audit Metadata