The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by analyzing file diffs, which creates a surface for indirect prompt injection if the files being committed contain malicious instructions.\n
Ingestion points: The skill reads output from git diff and git status commands in SKILL.md.\n
Boundary markers: No specific delimiters or XML tags are defined to isolate the diff content from the agent's instructions.\n
Capability inventory: The skill utilizes the Bash tool to execute git stage and git commit commands in SKILL.md.\n
Sanitization: There are no explicit instructions to sanitize or validate the content of the diffs to ignore potential embedded instructions.

git-commit