The Agent Skills Directory

[SAFE]: The skill consists purely of markdown instructions and does not include any executable code, shell scripts, or binary files. No malicious patterns such as obfuscation, credential harvesting, or unauthorized network access were found.
[PROMPT_INJECTION]: The skill processes external data (git commit messages) to generate output, which represents a surface for indirect prompt injection. However, the instructions do not implement unsafe interpolation and the risk is considered low and inherent to the intended text-transformation task.
Ingestion points: Git commit history (via git tool execution by the agent).
Boundary markers: Not explicitly defined in the provided markdown instructions.
Capability inventory: No scripts or subprocess calls are provided within the skill files themselves; the skill relies on the agent's native git integration.
Sanitization: No specific sanitization or filtering of commit content is described beyond the natural language transformation instructions.

changelog-generator