alterlab-genai-sound-effects
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from project-related files which could potentially contain malicious instructions.
- Ingestion points: The workflow in
SKILL.mdexplicitly instructs the agent to read existing project files, including scripts, video edits, and podcast outlines, to maintain creative continuity. - Boundary markers: The skill lacks explicit instructions or the use of clear delimiters to prevent the agent from following instructions that might be embedded within the processed project files.
- Capability inventory: The agent has the capability to perform web searches and write multiple structured markdown files (sound maps, prompt libraries, and architecture plans) to the local project directory.
- Sanitization: There is no evidence of content sanitization or validation protocols to filter out potential prompt injection attacks hidden in the metadata or text of the ingested project files.
Audit Metadata