The Agent Skills Directory

[SAFE]: The skill provides automated tools for migrating legacy RPG (Report Program Generator) code. The included scripts (e.g., extract-structure.py, generate-java-classes.py, analyze-dependencies.sh) perform static analysis on source files to identify data structures and logic patterns. All identified actions align with the primary migration use case.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted RPG source code provided by the user. While this creates a potential surface for indirect prompt injection if the source code contains malicious instructions, the skill does not interpolate this data into executable contexts (like shell commands or eval blocks) in a way that bypasses agent safety filters. The risk is inherent to the code analysis purpose and is mitigated by the static nature of the parsing.- [COMMAND_EXECUTION]: The provided Bash and PowerShell scripts utilize standard system utilities such as find, grep, sed, awk, and jq for file processing and dependency mapping. These operations are limited to the provided source directory and outputting results to the local filesystem, which is standard behavior for development and migration tools.- [OBFUSCATION]: Several reference files (e.g., references/pseudocode-rpg-advanced.md) contain terminal escape sequences (e.g., OSC 633 shell integration codes) that appear to be artifacts of a developer's environment rather than intentional obfuscation. These characters do not hide malicious payloads or interfere with the security of the skill.

rpg-migration-analyzer