skills/kursku/skills/docker-expert/Gen Agent Trust Hub

docker-expert

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various shell commands including docker, docker-compose, and find to analyze project structures and validate the status of containers (SKILL.md). \n- [REMOTE_CODE_EXECUTION]: The skill facilitates the execution of build instructions and runtime logic through docker build and docker run commands when validating local Dockerfiles and images (SKILL.md). \n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes contents from user-controlled configuration files without isolation. \n
  • Ingestion points: The skill searches for and reads Dockerfile* and *compose*.yml files in the local workspace (SKILL.md). \n
  • Boundary markers: None. The skill does not implement delimiters or instructions to ignore embedded commands within ingested files. \n
  • Capability inventory: The skill has access to high-capability tools such as docker build, docker run, and docker exec (SKILL.md). \n
  • Sanitization: There is no evidence of content filtering or validation for the configuration files it processes. \n- [EXTERNAL_DOWNLOADS]: The skill interacts with external services to pull container images and run security audits using Docker Scout, representing standard interactions with well-known container ecosystem services (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 12:02 PM
Security Audit — agent-trust-hub — docker-expert