ai-podcast-creation

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the belt CLI and other related skills using the npx skills add command, which fetches official vendor packages. It also links to external documentation for installation.
  • [COMMAND_EXECUTION]: The skill uses the Bash(belt *) tool to execute audio processing commands through the vendor's CLI. This execution is limited to the belt binary as specified in the skill configuration.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface in its script generation workflow. 1. Ingestion points: Ingests untrusted text via the <your-document-content> placeholder. 2. Boundary markers: No delimiters are present in the prompt template. 3. Capability inventory: Uses belt (Bash) for audio generation. 4. Sanitization: No sanitization is performed on user-supplied document content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 04:34 AM
Security Audit — agent-trust-hub — ai-podcast-creation