ln-700-project-bootstrap
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes a fallback mechanism to fetch shared files and reference documentation from the author's official GitHub repository (
github.com/levnikolaevich/claude-code-skills) using the WebFetch tool when local directories are absent.\n- [COMMAND_EXECUTION]: The bootstrap workflow and verification procedures involve executing standard development CLI tools includingnpm,dotnet,docker-compose, andcurlto manage dependencies, build projects, and verify service health.\n- [PROMPT_INJECTION]: During the technology detection phase, the skill ingests metadata from local project files (e.g.,package.json,.csproj,requirements.txt), which constitutes a potential surface for indirect prompt injection from untrusted codebases.\n - Ingestion points: Detection logic in
SKILL.mdandreferences/stack_detection.mdscans the project root and subdirectories.\n - Boundary markers: No specific delimiters or "ignore instructions" warnings are applied to the ingested file content before it is processed by the agent.\n
- Capability inventory: The skill and its delegated sub-skills possess extensive system capabilities, including file creation, script execution, and container management.\n
- Sanitization: Ingested file contents are parsed for technology patterns and versions but are not explicitly sanitized or escaped.
Audit Metadata