The Agent Skills Directory

[SAFE]: The skill performs standard repository analysis using git commands and local file operations. It does not exhibit any malicious patterns such as credential exfiltration, remote code execution, or unauthorized network access.
[INDIRECT_PROMPT_INJECTION]: The skill processes git commit history and changelog files which could theoretically contain malicious instructions. However, this is inherent to its primary purpose as an archaeology tool, and the risk is considered negligible for this specific use case.
Ingestion points: Repository metadata, commit messages, and the project's CHANGELOG.md file (file: SKILL.md).
Boundary markers: None identified; the skill processes the raw text output from git and the changelog file.
Capability inventory: The skill uses Bash, Read, and Write capabilities to execute git queries and save the final report.
Sanitization: No specific content sanitization is performed on the commit messages or changelog content before they are processed by the agent.

git-ai-archaeology