skills/sjinn-ai/skills/sjinn-compose/Gen Agent Trust Hub

sjinn-compose

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the sjinn CLI to perform video processing. It constructs shell commands by interpolating user-supplied video URLs and file paths into the --video-urls argument.
  • [EXTERNAL_DOWNLOADS]: The skill requires the @sjinn-build/cli package. As a vendor-owned resource (sjinn-ai), this is standard for the skill's functionality.
  • [DATA_EXFILTRATION]: Local video files or remote URLs are passed to the vendor's CLI, which involves transmitting these assets or their references to the vendor's infrastructure for processing.
  • [PROMPT_INJECTION]:
  • Ingestion points: Video URLs and local file paths provided by the user (SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or safety markers to prevent malicious filenames or URLs from influencing the command execution.
  • Capability inventory: The skill has the capability to execute subprocesses (sjinn compose) and write files to the local system (--download).
  • Sanitization: No sanitization or validation steps are defined to check the integrity or safety of the input strings before they are passed to the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 02:19 PM
Security Audit — agent-trust-hub — sjinn-compose