ops-journal

Automates logging of deployments, incidents, changes, and decisions into a searchable ops journal with incident timelines and postmortem generation.

This skill appears to be a local ops journal and is internally consistent. Before installing or running: (1) review the script source (already included) and confirm you're comfortable with files being written to ~/.openclaw/workspace/ops-journal (or set OPS_JOURNAL_DIR to a different folder); (2) run it as a non-privileged user — it only needs file-system access to that directory; (3) if you plan integrations (infra-watchdog or others), verify hooks only post expected messages and do not expose sensitive data in entries; (4) if you require network isolation, note the tool itself performs no network operations but any integrations you add might. If you want stronger assurances, run it in a sandbox/container first.

Type: OpenClaw Skill Name: ops-journal Version: 1.0.0 The skill is classified as suspicious due to a potential arbitrary file write vulnerability in the `scripts/journal.py` file. The `cmd_export` function allows writing journal entries to an arbitrary file path specified by the `--output` argument (`with open(args.output, 'w') as f:`). While this functionality is plausible for an export feature, it presents a significant vulnerability if a malicious actor or a compromised agent could control the `args.output` path, potentially leading to overwriting critical system files or user configuration files. There is no evidence of intentional malicious behavior such as data exfiltration, backdoors, or prompt injection in `SKILL.md`.