giving-presentations

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions were found that attempt to override system prompts or bypass safety guidelines.\n- [Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local files or perform unauthorized network operations.\n- [Obfuscation] (SAFE): No obfuscated content was detected.\n- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not install external packages or execute remote scripts.\n- [Indirect Prompt Injection] (SAFE): The skill processes untrusted user data to generate presentation content.\n
  • Ingestion points: SKILL.md (Step 1, Step 4) and references/INTAKE.md (Question 11).\n
  • Boundary markers: Absent; no specific delimiters or warnings are used for user content.\n
  • Capability inventory: The skill is limited to Markdown text generation and does not have access to subprocess, network, or file-write tools.\n
  • Sanitization: Absent.\n- [Dynamic Execution] (SAFE): No evidence of runtime code generation or dynamic loading.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:52 PM