invoice-generator
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions or metadata.
- [INDIRECT_PROMPT_INJECTION]: The agent processes unstructured user-provided project descriptions to generate JSON output. While this represents a data ingestion surface, the risk is mitigated by the agent's limited role. \n
- Ingestion points: Project descriptions provided via prompts as described in
agents/devis.md. \n - Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore embedded instructions in the input. \n
- Capability inventory: The agent's role is strictly limited to generating JSON text; it lacks the capability to execute shell commands, perform network operations, or read sensitive files itself. \n
- Sanitization: No specific sanitization or escaping logic is defined for the output fields.
- [DATA_EXPOSURE]: The skill handles business-related data (client names, emails) as part of its primary function. This behavior is within the intended scope and follows standard data processing practices for invoice generation.
Audit Metadata