book-architect

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is composed of markdown documentation and prompt templates for book planning. It does not perform any automated actions or system modifications.
  • [NO_CODE]: There are no scripts, binaries, or shell commands included in the skill. All operations are performed by the user/agent through natural language prompts.
  • [DATA_EXFILTRATION]: No network tools (curl, wget) or file access patterns are present, precluding the possibility of unauthorized data transfer.
  • [PROMPT_INJECTION]: Ingestion points: User-provided niche, primary keyword, and pain points in SKILL.md. Boundary markers: Input variables are enclosed in brackets (e.g., [TOPIC]) but lack strict 'ignore' instructions. Capability inventory: No file system access, no network operations, and no command execution across the skill. Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 03:30 PM
Security Audit — agent-trust-hub — book-architect