The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell commands to analyze the project's versioning history and commit logs. These commands are used locally and do not involve network operations or administrative privileges.
Evidence: Uses git tag, git log, git describe, grep, cat, and head in SKILL.md to detect versioning patterns and extract commit messages.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain malicious instructions intended to influence the agent's behavior.
Ingestion points: Git commit messages retrieved via git log and project documentation files like CHANGELOG.md and CLAUDE.md (referenced in SKILL.md workflow steps).
Boundary markers: Absent. The skill does not provide instructions to the agent on how to distinguish between legitimate commit data and potential embedded instructions.
Capability inventory: The skill's capabilities are limited to local file reading and git metadata inspection. It lacks high-risk capabilities such as network exfiltration, sensitive file access, or dynamic code execution.
Sanitization: Absent. The skill extracts and formats text directly from the commit history without filtering or escaping content.

changelog-generator