skills/fancive/claude-skills/teacher/Gen Agent Trust Hub

teacher

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process untrusted data from external sources and local files.
  • Ingestion points: The 'Research Phase' explicitly instructs the agent to use web_search and read_web_page for external content, and Read, Grep, and finder for local codebase analysis (documented in SKILL.md).
  • Boundary markers: The instructions do not define any delimiters or provide warnings to the agent to ignore potentially malicious instructions embedded within the researched materials.
  • Capability inventory: The skill utilizes file system discovery (finder), file reading (Read, Grep), and network requests (web_search, read_web_page).
  • Sanitization: There are no instructions provided to sanitize or validate the content retrieved from the web or local files before it is processed by the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 04:20 PM