requirements-quality
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (HIGH): The skill possesses a high-risk attack surface as it is designed to ingest untrusted external requirements data while having file-system modification capabilities. * Ingestion points: External files processed via commands like
/spec:validateand/spec:refineinSKILL.md. * Boundary markers: Absent; no delimiters are used to separate untrusted data from agent instructions. * Capability inventory: GrantedWrite,Edit, andTasktools inSKILL.mdmetadata, allowing side effects on the host. * Sanitization: Absent; no evidence of input validation or sanitization.
Recommendations
- AI detected serious security threats
Audit Metadata