technical-writer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): This skill has an inherent surface for indirect prompt injection as it processes user-provided topics and code. Since its output is purely informational text, the risk is categorized as low.
  • Ingestion points: The skill processes user-supplied technical topics and code snippets within the SKILL.md templates.
  • Boundary markers: No specific delimiters or boundary instructions are included to prevent the agent from following instructions embedded in the user content.
  • Capability inventory: The skill is entirely instructional and does not possess capabilities for file manipulation, command execution, or network communication.
  • Sanitization: No sanitization or validation of the input content is implemented.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 06:27 AM