The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external software repositories, which serves as an ingestion point for indirect prompt injection attacks.
Ingestion points: The scripts/analyze_complexity.py script reads and analyzes the text of files within target repositories provided by the user.
Boundary markers: There are no specific instructions in SKILL.md to use delimiters or security warnings when presenting code analysis or extracted code snippets to the agent context.
Capability inventory: The skill allows for recursive file reading within a directory and can perform code modifications if explicitly instructed by the user.
Sanitization: The script performs heuristic scanning and AST parsing but does not implement sanitization to filter out malicious natural language instructions embedded in code comments or strings.

complexity-optimizer