shownotes-generator
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted longform content such as transcripts and articles, which creates a surface for indirect prompt injection attacks where malicious instructions are hidden in the source data. The skill includes a manual step requiring the user to confirm inferred metadata, which serves as a human-in-the-loop verification.
- Ingestion points: User-provided longform content processed in SKILL.md.
- Boundary markers: Explicit instructions to confirm inferred metadata with the user before generating the full summary.
- Capability inventory: Limited to text generation and markdown formatting.
- Sanitization: No specific input sanitization or filtering logic is provided.
- [NO_CODE]: The skill does not contain any executable scripts, binaries, or automated installation commands. It relies entirely on descriptive prompts and formatting examples.
Audit Metadata