inkos-story-import
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution were found in the skill instructions or the reconstruction rubric.- [INDIRECT_PROMPT_INJECTION]: The skill processes external manuscripts, which constitutes a data ingestion surface. However, the risk is minimal as the skill does not possess dangerous tools or capabilities to exploit. * Ingestion points: User-provided manuscripts and reference materials processed via SKILL.md. * Boundary markers: None present. * Capability inventory: No network access, sensitive file access, or shell command execution capabilities identified. * Sanitization: None present.
Audit Metadata