The Agent Skills Directory

[SAFE]: Extensive analysis of the skill's instructions and operations revealed no malicious patterns, data exfiltration attempts, or unauthorized external references.
[COMMAND_EXECUTION]: The skill includes a shell script snippet for prerequisite validation. This script safely iterates through a hardcoded list of file paths to verify their existence before proceeding with documentation analysis.
[PROMPT_INJECTION]: The skill contains a documentation processing surface that could be used for indirect prompt injection. Ingestion points: The skill reads 11 documentation files from the docs/reverse-engineering/ directory. Boundary markers: No explicit delimiters or instructions are used to distinguish ingested data from the skill's operational logic. Capability inventory: The skill is limited to reading markdown files and writing extracted specifications to the _portable-extract/ directory; it possesses no network access or shell-execution capabilities for untrusted data. Sanitization: No specific sanitization of the input documentation content is performed. This surface is considered low risk given the skill's limited capabilities.

portable-extract