baoyu-compress-image

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The file scripts/main.ts executes system commands including sips, cwebp, and convert (ImageMagick) via child_process.spawn to handle image processing tasks.
  • [EXTERNAL_DOWNLOADS]: The skill invokes npx -y bun to run its logic and dynamically imports the sharp library if needed for compression, which involves fetching external packages from public registries.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface.
  • Ingestion points: The script reads arbitrary file names from the user's file system during image processing.
  • Boundary markers: Results and file paths are printed to standard output without delimiters or boundary markers, which could allow malicious filenames to influence the agent's next actions if it interprets the output as instructions.
  • Capability inventory: The skill has the ability to modify the file system (deleting original files via unlinkSync and renaming via renameSync) and execute subprocesses.
  • Sanitization: File names and paths are not escaped or sanitized before being output to the console for the agent to read.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 03:19 AM
Security Audit — agent-trust-hub — baoyu-compress-image