quality-management-expert
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data into its quality management logic.\n
- Ingestion points: Data ingestion happens in
references/EXAMPLES.mdvia thenc_dataandfinding_datadictionaries which store user-provided descriptions of quality issues.\n - Boundary markers: There are no explicit instructions or delimiters to prevent the agent from following instructions hidden within audit finding descriptions or nonconformance reports.\n
- Capability inventory: The skill is granted
WriteandWebSearchpermissions inSKILL.md, providing a potential sink for malicious instructions found in processed data.\n - Sanitization: The provided implementation logic does not include sanitization or validation of input strings before they are stored or processed by the quality management system.
Audit Metadata