series-architect

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional templates and Markdown documentation for creative writing planning. It does not contain any executable scripts, binaries, or shell commands.
  • [DATA_EXFILTRATION]: The skill requests file:read and file:write permissions to manage series data within the workspace/memory/book-bible/ directory. This is consistent with its stated purpose of creating a series bible. No hardcoded credentials or network operations to external domains were detected.
  • [PROMPT_INJECTION]: The instructions are strictly task-oriented and do not include directives to bypass safety filters, override agent constraints, or reveal system prompts.
  • [COMMAND_EXECUTION]: There are no instances of command execution, dynamic context injection, or persistence mechanisms within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 07:41 PM
Security Audit — agent-trust-hub — series-architect