Training Manager
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: openclaw-training-manager Version: 0.1.4 The OpenClaw Training Manager skill bundle is benign. It demonstrates a strong focus on security, particularly against prompt injection and shell injection. The `SKILL.md` instructs the AI agent to use dedicated, sanitized scripts for all file operations and to perform agent-level screening of user input. A centralized `scripts/lib/security.sh` library provides robust tiered prompt injection filtering, shell metacharacter validation, and rate limiting. All scripts handling user input (`generate-skill.sh`, `log-training.sh`, `write-file.sh`) correctly implement these security measures, including path traversal prevention and input validation. There is no evidence of malicious intent, data exfiltration, unauthorized remote control, or persistence mechanisms.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing and using this skill can change how your agent behaves in later sessions.
The skill includes a writer that can modify core OpenClaw workspace files. The filename whitelist, overwrite protection, rate limiting, and injection checks make this purpose-aligned, but these are still important behavior-control files.
Allowed: SOUL.md, AGENTS.md, USER.md, TOOLS.md, IDENTITY.md, MEMORY.md
Review proposed edits to core workspace files before accepting them, and keep backups before major changes.
Incorrect, sensitive, or overly broad training notes could persist and shape future agent responses.
The skill intentionally stores user preferences, corrections, behavioral rules, and facts into persistent memory/context files that may influence future agent behavior.
corrections and preferences get categorized and logged automatically: Behavioral rules → `AGENTS.md` ... Facts → `MEMORY.md` or daily logs
Do not store secrets in training files, periodically review MEMORY.md and daily logs, and remove or correct stale instructions.
You have less independent context for who maintains the code or where updates come from.
The registry metadata does not provide a clear source or homepage for a skill that ships executable bash scripts. The provided scripts are readable and local, but provenance is still limited.
Source: unknown; Homepage: none
Inspect the included scripts before use and install updates only from a trusted ClawHub listing or verified repository.