skillshare-devcontainer

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to facilitate command execution within a Docker devcontainer. It provides specific instructions for running project-specific CLI tools, build tools, and test suites inside a Linux environment using docker exec.
  • [COMMAND_EXECUTION]: The skill uses eval "$(credential-helper --eval off)" to toggle authentication during testing, which involves local shell command execution to modify the environment.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) due to its design as a command runner:
  • Ingestion points: The skill ingests user-supplied content via the argument-hint defined in SKILL.md (e.g., "command-to-run").
  • Boundary markers: There are no explicit boundary markers or instructions to delimit or ignore instructions within the user-provided command strings.
  • Capability inventory: The skill utilizes docker exec and bash -c throughout SKILL.md, providing broad access to the container's environment and the bind-mounted workspace.
  • Sanitization: The skill does not describe any sanitization, validation, or escaping of the user-provided input before it is passed to the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:49 PM
Security Audit — agent-trust-hub — skillshare-devcontainer