slidev
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions were found that attempt to bypass safety filters or override agent constraints.
- [Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive system paths (like SSH keys or AWS credentials) and contains no hardcoded secrets.
- [External Downloads & Remote Code Execution] (SAFE): The skill uses local
pnpmcommands to build and run the presentation; it does not download or execute remote scripts from untrusted sources. - [Obfuscation] (SAFE): No hidden, encoded, or deceptive content (like Base64 or zero-width characters) was detected.
- [Indirect Prompt Injection] (SAFE): The skill ingests markdown files for presentation content as part of its primary purpose, but no exploitable capability or lack of sanitization was identified.
Audit Metadata