skills/yiweiwan/skills/speaker-notes/Gen Agent Trust Hub

speaker-notes

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's instructions are focused entirely on assisting the user with writing and formatting speaker notes for presentations. No malicious behavior or suspicious code patterns were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process slide content provided by the user. While this creates a surface for indirect prompt injection, the skill lacks any capabilities to execute commands, access the network, or write to the file system, mitigating the risk.
  • Ingestion points: Processes slide titles and content as described in the workflow section of SKILL.md.
  • Boundary markers: Not explicitly defined in the prompt instructions.
  • Capability inventory: No dangerous capabilities; the skill only outputs text.
  • Sanitization: No explicit sanitization or filtering of input content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 11:51 PM
Security Audit — agent-trust-hub — speaker-notes