video-summary
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted content (video transcripts and subtitles) which is then interpolated into a structured request for an LLM summary. This creates a surface for indirect prompt injection if the video content contains malicious instructions intended to manipulate the LLM's output.
- Ingestion points: Transcripts are fetched via
yt-dlpor generated locally usingopenai-whisperwithin thevideo-summary.shscript. - Boundary markers: The
call_llmfunction invideo-summary.shincorporates the transcript text into a summary prompt without utilizing distinct delimiters or instructions for the LLM to ignore embedded commands within the transcript. - Capability inventory: The script performs file system reads (for cookies and local videos), writes temporary files to
/tmp, and executes several CLI tools includingyt-dlp,ffmpeg, andwhisper. - Sanitization: A
clean_subtitlefunction is present invideo-summary.shto remove technical subtitle formatting (like WebVTT/SRT tags), though it does not filter the semantic content of the speech. - [COMMAND_EXECUTION]: The main execution script
video-summary.shorchestrates several third-party binaries (yt-dlp,ffmpeg,jq,whisper) via shell subprocesses. While arguments are generally quoted to prevent simple command injection, the skill's safety relies on the robustness of these external tools when processing potentially malformed video metadata or content from remote URLs.
Audit Metadata