podcast-to-content-suite

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process untrusted podcast transcripts, which could theoretically contain instructions to manipulate the agent's output.
  • Ingestion points: User-provided transcript text within the Markdown structure.
  • Boundary markers: Absent. The instructions do not define clear delimiters to separate transcript data from instructions.
  • Capability inventory: None. The skill only generates text for marketing collateral (blog posts, social threads, newsletters) and has no access to external tools, filesystem, or network resources.
  • Sanitization: Absent.
  • [Static Analysis] (SAFE): The skill contains no executable scripts, binaries, or configuration files that could facilitate unauthorized actions. It is strictly a prompt-based template.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 07:49 AM