ai-podcast-creation

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection in the 'NotebookLM-Style Content' workflow.
  • Ingestion points: Untrusted data enters the agent context via the '' placeholder in SKILL.md during script generation.
  • Boundary markers: Absent. The external content is interpolated directly into the prompt without clear delimiters or 'ignore' instructions.
  • Capability inventory: The skill possesses the Bash(infsh *) capability (defined in SKILL.md frontmatter), which allows execution of various AI applications on the inference platform.
  • Sanitization: No sanitization or validation of the input document is performed prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 06:35 PM
Security Audit — agent-trust-hub — ai-podcast-creation