write

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user input that could contain malicious instructions designed to influence the final prose or the behavior of the reviewer agent.
  • Ingestion points: User context is gathered via the $ARGUMENTS variable and the AskUserQuestion function as defined in SKILL.md.
  • Boundary markers: The instructions do not define clear delimiters (e.g., XML tags or triple quotes) to separate user-provided context from the system's own instructions.
  • Capability inventory: The skill performs file system write operations (creating draft-{topic-slug}.md) and invokes secondary agents (writing-reviewer), which could be manipulated if the input is not handled safely.
  • Sanitization: There is no explicit logic described for sanitizing or escaping the user's input before it is passed to the generation or review stages.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:34 AM