The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its core function of analyzing external, untrusted codebases.
Ingestion points: The LegacyCodeAnalyzer in references/system-assessment.md reads and processes the contents of all files in a target directory.
Boundary markers: There are no explicit markers or 'ignore embedded instructions' warnings applied to the data being read from the legacy files.
Capability inventory: The skill uses ast.parse and file reads for assessment, subprocess.run for git logging, and httpx for network proxying during framework migration.
Sanitization: The assessment scripts use structured parsing (AST) rather than execution, and command-line operations use list-based arguments to prevent shell injection, minimizing the risk of the agent being tricked by malicious file content or names.

legacy-modernizer