series-architect
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate writing assistant that organizes story planning data. No signs of malicious code, obfuscation, or unauthorized data exfiltration were found. The requested file permissions are used exclusively for creating and maintaining story 'bibles'.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes user-provided story concepts and workspace files during continuity checks. Ingestion points: Processes user input for characters and arcs, and reads files from 'workspace/memory/book-bible/'. Boundary markers: Absent in the current instructions. Capability inventory: Possesses 'file:read' and 'file:write' permissions. Sanitization: No explicit sanitization of input data is defined.
Audit Metadata