Monitor agent identity drift using git history. Detects when AI agents quietly modify their own SOUL.md, IDENTITY.md, AGENTS.md, or memory files — autonomy e...

What to consider before installing/using DriftWatch: - Functional fit: The script does what it claims: it reads your repo/git history, computes diffs for identity files, and writes a markdown report. Running the heuristic-only mode (--no-llm) is low-risk and stays entirely local. - LLM / data exfiltration risk: Enabling LLM analysis causes the tool to call the 'claude' CLI and submit git diffs (snippets) to Anthropic. That can transmit sensitive agent identity content and memory snippets off your machine. The registry metadata does NOT declare ANTHROPIC_API_KEY or the 'claude' binary requirement — so the privacy/credential implication is not made explicit. - Missing declarations: The skill uses 'git' and 'claude' via subprocess.run and implicitly requires the Anthropic credential/CLI configuration, but these runtime dependencies are not listed in the skill metadata. Treat LLM mode as networked and external by default. - Recommended safe steps: - Inspect the code (you already have it). Confirm the WORKSPACE path and TRACKED_FILES align with where you want to run it. - Run first with --no-llm to generate a heuristic-only, local report. - If you need LLM analysis, prefer running it in an environment where you control the Anthropic key and are comfortable sending those diffs externally; explicitly set and review the 'claude' CLI configuration first. - Consider editing TRACKED_FILES or the WORKSPACE constant to limit what is read, or replace the LLM call with a local model if you want semantic analysis without network exposure. - Add this to a sandboxed environment or CI job with least privilege if you will run it automatically (cron/heartbeat). - When to be cautious: Do not enable LLM mode if the tracked files contain secrets, personally identifiable information, or memory entries you do not want sent to an external provider. Also verify that the script's WORKSPACE path does not point outside your intended repository. If you want, I can point to the exact lines that invoke 'claude' and show the code locations that read files and set WORKSPACE so you can more easily review or modify them.

Type: OpenClaw Skill Name: driftwatch Version: 1.0.0 DriftWatch is a security-oriented utility designed to monitor changes to agent identity and configuration files (e.g., SOUL.md, AGENTS.md) using git history. The script (driftwatch.py) uses standard subprocess calls to 'git' and an optional 'claude' CLI for semantic analysis of diffs, which aligns perfectly with its stated purpose of detecting 'identity drift' in AI agents. There are no signs of data exfiltration, unauthorized persistence, or malicious execution; the tool is read-only regarding the workspace and only outputs human-readable reports or JSON data locally.