The Agent Skills Directory

[SAFE]: The skill follows standard practices for developer-oriented tools. It interacts with the local file system and git repository within the expected scope of an experiment resume tool.
[INDIRECT_PROMPT_INJECTION]: There is a potential attack surface where the skill reads data from external files (program.md and results.tsv) that could contain untrusted content. However, the skill's current logic is limited to summarizing this data for the user, which is a low-risk operation.
Ingestion points: The skill reads program.md and results.tsv in SKILL.md (Step 2).
Boundary markers: No explicit delimiters or safety instructions are used when reading these files.
Capability inventory: The skill utilizes shell execution for git and python (as seen in SKILL.md).
Sanitization: No explicit sanitization or validation of the file content is mentioned.

ar-resume