suggest-sfx
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local Python scripts
tools/gen_sfx.pyandtools/mix_sfx.pyto automate the audio production workflow within the project workspace. - [PROMPT_INJECTION]: The skill processes external data (video timelines and transcripts) to create sound effect plans, identifying a potential surface for indirect prompt injection.
- Ingestion points: Processes data from
videos/video-N/work/timeline.json,videos/video-N/work/edited-transcript.json, and animation source files inremotion/src/shots/video-N/*.tsx. - Boundary markers: No explicit instruction delimiters or boundary markers were identified in the provided instructions.
- Capability inventory: The skill is capable of executing local Python tools and performing network API calls via
tools/gen_sfx.py. - Sanitization: The skill enforces a mandatory human-in-the-loop
USER-AUDIT GATEwhere the user must explicitly approve thesfx-plan.jsonartifact before the agent proceeds to mixing or generation.
Audit Metadata