Moltbook Collection Agent
Security checks across static analysis, malware telemetry, and agentic risk
Overview
The skill mostly does what it describes (collecting and enriching MoltBook data and scheduling runs), but there are several incoherences and risky choices — most notably a hard-coded GitHub token in config.py, mismatched environment-variable names in docs vs code, and instructions that install cron entries and run remote install scripts — so proceed with caution.
Key things to consider before installing or running this skill: - Do not run the README's suggested 'curl | bash' without reviewing the script; prefer cloning the repo and inspecting install.sh locally. - Inspect config.py and remove any embedded credentials. The repository includes a hard-coded GITHUB_TOKEN — treat that as compromised: do not use it, and do not assume it is safe. If you fork/use this skill, replace that value with an environment variable you control, and verify the token's scope (use a fine-grained PAT with minimal permissions). - Verify which env var the code actually reads (GITHUB_TOKEN) and set that yourself (do not export GH_PUSH_TOKEN unless you update code or set both). Prefer a token with only the permissions needed (repo:contents for a single repo or an empty-scope token for testing). - Expect the scheduler to modify your user crontab. If you do not want autonomous periodic runs, do not run scheduler.install; run the agent manually instead. - Run the code in an isolated environment (dedicated account or container) and review where data is pushed (GITHUB_REPO defaults to the author's repo). If you want to push to your own repo, set GITHUB_REPO and a PAT scoped to that repo. - If you are unsure about the embedded token's validity, assume it is compromised: rotate any of your tokens that may have been exposed and do not reuse tokens found in third-party code. Given the credential embedding and several documentation/code mismatches, treat this package as suspicious until the author removes hard-coded secrets and clarifies expected env vars and install steps.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
No VirusTotal findings
Risk analysis
No visible risk-analysis findings were reported for this release.