automate-this
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local system commands including ffmpeg, ffprobe, and uname to process media files and identify system capabilities for script generation.
- [PROMPT_INJECTION]: The skill processes user-provided audio transcripts, which represents an indirect prompt injection surface as the content of the narration directly influences the logic of the generated automation scripts. This finding is noted as a risk factor for the script generation process (Ingestion: audio.txt; Capability Inventory: script generation and terminal execution; Sanitization/Boundaries: Absent).
Audit Metadata