tufte-slide-design

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists exclusively of Markdown files (SKILL.md, references/slide-checklist.md, references/tufte-principles.md). There are no scripts, binaries, or configuration files that execute logic on the host system.
  • [PROMPT_INJECTION] (SAFE): The instructions focus on design principles and do not contain any attempt to override agent behavior, bypass safety filters, or extract system prompts.
  • [DATA_EXFILTRATION] (SAFE): No network commands (curl, wget) or credential markers were found. The skill does not access sensitive local file paths.
  • [REMOTE_CODE_EXECUTION] (SAFE): There are no external dependencies, package managers, or remote script download patterns.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process user-provided data to generate slides. While this represents a surface for untrusted data ingestion, the skill lacks the capabilities (file writes, network access, subprocess execution) required to turn an injection into a functional exploit.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:26 PM