cinematic-prompting
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided text prompts to rewrite them using technical lexicon. While this represents a data ingestion surface, the skill does not utilize any tools, network operations, or file system access, effectively neutralizing risks associated with malicious instructions in the input data.
- Ingestion points: Processes user prompts provided in text (SKILL.md).
- Boundary markers: Instructions specify returning only the enhanced prompt unless feedback is requested.
- Capability inventory: None. The skill only generates text output and does not invoke external tools or scripts.
- Sanitization: No explicit sanitization of input text is performed as it is used for prompt transformation.
Audit Metadata