The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes data from the repository being analyzed. 1. Ingestion points: repository content is ingested via the impact() tool, detect_changes() tool, and the READ command for gitnexus:// URIs. 2. Boundary markers: the skill lacks explicit boundary markers or instructions to the agent to ignore instructions embedded within the ingested repository data. 3. Capability inventory: the agent has capabilities for file reading and terminal command execution. 4. Sanitization: no sanitization or escaping of the repository-sourced data is mentioned.
[COMMAND_EXECUTION]: The skill includes instructions to execute a local script file (node .gitnexus/run.cjs analyze) to update the code index. This script is a local resource associated with the tool's functionality.

gitnexus-impact-analysis