skills/howells/fiction/outline/Gen Agent Trust Hub

outline

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill's behavior is consistent with its stated purpose of document generation.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes user-provided command arguments and existing project architecture documents to generate output. However, the risk is negligible as the skill only performs local text generation and file updates.
  • Ingestion points: User-supplied command arguments via the $ARGUMENTS placeholder and local story architecture files.
  • Boundary markers: None present; the skill treats architecture files and arguments as direct input for the outliner agent.
  • Capability inventory: Spawning internal agents (fiction:outliner), reading local architecture files, and writing or updating project files (README or outline documents).
  • Sanitization: No explicit validation or sanitization of the input documents or arguments is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 05:14 AM
Security Audit — agent-trust-hub — outline