skills/itumulak/kahanas/dev-audit/Gen Agent Trust Hub

dev-audit

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes code review reports located in the .konteksto/reviews/ directory. Because these reports are generated based on external code or tool outputs, they represent an attack surface where malicious instructions could be embedded. If the agent ingests a report containing such instructions, it could influence the agent's behavior or logic during the audit register update process. The skill lacks defined validation or sanitization procedures for this ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 11:42 AM