The Agent Skills Directory

PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection because it analyzes data from git diff. Malicious instructions in the code being analyzed could influence the resulting commit message.\n
Ingestion points: git diff and git diff --staged in SKILL.md.\n
Boundary markers: Absent. No instructions provided to delineate code from instructions.\n
Capability inventory: git commit in SKILL.md.\n
Sanitization: Absent.\n- COMMAND_EXECUTION (SAFE): The skill uses git diff and git commit to perform its intended tasks. These are standard commands for version control and do not represent a security risk in this context.

commit-helper