fountain-clip-finder
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The Python script
modules/external-source/scripts/read-segments.pyexecutes external command-line tools to process video and audio data.\n - It uses
subprocess.runto callyt-dlp,ffmpeg, andffprobefor metadata extraction and transcription tasks.\n - User-provided URLs and file paths are passed as arguments to these tools. While
shell=Trueis not used, this remains a significant capability.\n- [EXTERNAL_DOWNLOADS]: The skill usesyt-dlpto fetch caption tracks and metadata from YouTube watch pages.\n - Evidence:
download_captionsandfetch_caption_wordsfunctions inmodules/external-source/scripts/read-segments.py. YouTube is a well-known service, making this a legitimate operation for the skill's purpose.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted transcript content from external sources (YouTube or local files) which is then used to generate social media copy, posing a risk of indirect prompt injection.\n - Ingestion points: Transcripts are read from YouTube or local files in
modules/external-source/scripts/read-segments.pyand passed through thediscoveryandboundariesmodules.\n - Boundary markers: The
modules/copy/MODULE.mdinstructions do not specify the use of clear delimiters or instructions to ignore embedded commands when interpolating transcript text into prompts for generating labels and post text.\n - Capability inventory: The skill can execute shell commands via
subprocess(in theexternal-sourcemodule) and publish draft posts via the Fountain Social API.\n - Sanitization: A "safety pass" is mentioned in
modules/copy/MODULE.mdfor content risks, but no specific sanitization for prompt injection is described for the ingested transcript data.
Audit Metadata