The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted external data, specifically Dockerfiles and image references provided by the user. This creates a standard ingestion surface where external content is processed by the agent.\n
Ingestion points: User-supplied image tags and local Dockerfile content.\n
Boundary markers: The instructions do not specify the use of delimiters or boundary markers when reading or processing external file content.\n
Capability inventory: The skill utilizes shell execution (Bash), file modification (Edit, Write), and a specialized security scanning tool (mcp_snyk_snyk_container_scan).\n
Sanitization: No explicit sanitization or validation of the ingested file content is performed before analysis.\n- [COMMAND_EXECUTION]: The skill requires the use of shell commands to manage container images and verify security fixes as part of a standard development workflow.\n
Evidence: The instructions guide the agent to perform docker build for rebuilding images, as well as docker pull and docker login for managing registry access during the scan and remediation phases.

container-security