skills/mukul975/anthropic-cybersecurity-skills/securing-container-registry-images/Gen Agent Trust Hub
securing-container-registry-images
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads installation scripts for security tools (Syft, Grype) from Anchore's official GitHub repository.
- [REMOTE_CODE_EXECUTION]: Implementation instructions include piping remote scripts directly to the shell to facilitate tool setup in the execution environment.
- [COMMAND_EXECUTION]: The
scripts/agent.pyfile executes external security binaries (Trivy, Syft, Cosign) via thesubprocessmodule to perform scanning and signing operations. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing external container image names.
- Ingestion points: User-provided image references enter the script through the
--imageargument inscripts/agent.py. - Boundary markers: Image names are interpolated directly into command lists without delimiters or explicit instruction isolation.
- Capability inventory: The script possesses the capability to execute system commands via
subprocess.run(inscripts/agent.py). - Sanitization: No validation or escaping is performed on the image name strings before they are passed to the underlying CLI tools.
Audit Metadata