Skills
Navigate
skills/bruin-data/agent-resource-kit/record-terminal-demo/Gen Agent Trust Hub

record-terminal-demo

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/render_demo.py executes system utilities vhs, ffmpeg, and ffprobe using the subprocess module. This is the intended behavior for the skill's purpose of automating terminal recording and validation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes .tape files containing shell instructions. This represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Reads .tape files provided by the user or existing in the workspace (SKILL.md, scripts/render_demo.py).
  • Boundary markers: None explicitly defined for tape content, though the VHS format provides a structured boundary.
  • Capability inventory: Executes shell commands via VHS and performs file/image processing with ffmpeg (scripts/render_demo.py).
  • Sanitization: Uses shlex for parsing tape directives in the helper script, but the content of the commands within the tape is executed by the VHS tool as intended.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 04:40 PM