pedagogy-review

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
  • Ingestion points: The skill reads external content from .tex, .qmd, and .typ files provided as user arguments.
  • Boundary markers: No delimiters or explicit instructions to ignore embedded commands are used during content processing.
  • Capability inventory: The agent is permitted to use Read, Write, and Task tools, allowing for file system access and execution of other agent tasks.
  • Sanitization: There is no validation or sanitization of the file contents before they are passed to the reviewer agent.
  • [NO_CODE]: The skill consists exclusively of markdown instructions in SKILL.md and does not distribute any executable scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:16 AM