writing-fragments

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for creative writing and brainstorming. It manages a local markdown file by appending user-provided fragments. No malicious code, obfuscation, or data exfiltration patterns were identified.
  • [PROMPT_INJECTION]: The skill reads from a user-specified markdown file before each write operation to preserve user edits. This ingestion of external data constitutes a surface for indirect prompt injection, as the agent may process instructions placed in the file. Ingestion points: Markdown file at user-specified path. Boundary markers: None. Capability inventory: File read and write. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:26 AM
Security Audit — agent-trust-hub — writing-fragments