my-homework-new

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied homework content and inserts it into a markdown file, creating an indirect prompt injection surface. * Ingestion points: User input gathered in Step 2. * Boundary markers: None identified in the template instructions. * Capability inventory: File-write access to the local directory (docs/camp/). * Sanitization: No input validation or escaping is performed on user input.
  • [COMMAND_EXECUTION]: The skill instructs the agent to create markdown files at specific local paths (docs/camp/ai_native_camp_dayN_homework.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 03:23 PM