The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill is designed to guide users through scientific experimentation steps.
[PROMPT_INJECTION]: The skill processes untrusted data by reading hypothesis cards from the local repository. This represents a surface for indirect prompt injection, though it is inherent to the skill's primary function.
Ingestion points: Reads hypothesis files located at hypotheses/H-NNN.md in Step 1.
Boundary markers: None identified in the provided instructions.
Capability inventory: The skill suggests writing shell scripts, Makefiles, and Dockerfiles to the local filesystem (Step 3).
Sanitization: No explicit sanitization or validation of the input file content is defined.

research-experiment