The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data (code changes, file contents) which presents a surface for indirect prompt injection.
Ingestion points: The skill instructions in SKILL.md direct the agent to gather information from modified files and git command output.
Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to ignore potentially malicious instructions embedded within the code comments or content being summarized.
Capability inventory: The skill utilize Read, Glob, Grep, and Bash tools to analyze project files.
Sanitization: There is no evidence of data sanitization or validation of the ingested file content before it is processed by the model for summarization.

summarize-changes