ai-ethics-compliance
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides guidelines for assessing bias, fairness, and legal compliance (GDPR, EU AI Act). It does not include any scripts, external dependencies, or commands that could be exploited for malicious purposes.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to audit external data, such as training sets or RAG sources, which introduces an ingestion point for untrusted content.
- Ingestion points: External training/RAG data mentioned in the "Dataset Audit" section of SKILL.md.
- Boundary markers: Absent; there are no specific instructions to use delimiters or ignore embedded instructions in the ingested data.
- Capability inventory: No file system access, shell execution, or network tools are defined within this skill.
- Sanitization: Absent; the skill does not specify any validation or sanitization methods for the data processed during audits.
Audit Metadata