alterlab-cdm-sound-designer
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting external data from project files and web searches to generate sound design deliverables, which presents a surface for potential indirect prompt injection attacks.
- Ingestion points: The workflow involves reading external content such as screenplays, director's notes, and web search results as specified in the workflow section of SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or guidance to treat external content as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill is authorized to perform web searches, read project-related files, and write structured markdown files to the project directory (SKILL.md).
- Sanitization: There are no defined mechanisms for sanitizing, filtering, or validating the content retrieved from external sources before it is processed by the agent.
Audit Metadata