ai-podcast-creation

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data (documents) to generate podcast scripts via the Claude model, creating a potential surface for indirect prompt injection.
  • Ingestion points: Document content provided in the 'NotebookLM-Style Content' section of SKILL.md.
  • Boundary markers: Absent; the templates do not use specific delimiters or instructions to ignore instructions within the data.
  • Capability inventory: The skill is permitted to run Bash commands with the 'infsh' tool in SKILL.md, which involves remote application execution and file handling.
  • Sanitization: Absent; document content is interpolated directly into prompts without filtering.
  • [EXTERNAL_DOWNLOADS]: The skill references and suggests the installation of additional modules from the official 'inference-sh/skills' repository. These are vendor-owned resources and are documented as legitimate dependencies of the platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 10:41 PM