skills/kriscard/skills/learn/Gen Agent Trust Hub

learn

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust instructional framework without introducing dangerous capabilities. It uses specific platform tools for documentation lookup (mcp__context7__resolve-library-id and mcp__context7__query-docs) within their intended scope to ensure teaching materials remain current and accurate.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided topics and answers through an interactive loop, which represents a surface for indirect prompt injection.
  • Ingestion points: The $ARGUMENTS variable and responses gathered via the AskUserQuestion tool in SKILL.md.
  • Boundary markers: Absent; the skill relies on natural language flow for processing user input.
  • Capability inventory: Limited to library ID resolution, documentation queries, and triggering the til skill for note persistence; no high-privilege capabilities like arbitrary file writes or system command execution are exposed.
  • Sanitization: Absent; user-provided content is passed directly to documentation tools and session-saving summaries without explicit filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 06:36 PM
Security Audit — agent-trust-hub — learn