Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed daily research digest that searches public sources and saves local digest files, with privacy and scheduling considerations but no evidence of hidden or malicious behavior.
Install only if you are comfortable with an agent periodically querying third-party services using your configured project keywords and keeping local digest and seen-URL files. Prefer explicit manual invocation or a clearly configured schedule if you do not want automatic morning runs.
The skill description emphasizes convenience but does not clearly warn that it automatically scans external services and persists results in local state files. Users or orchestrating agents may invoke it without informed consent, leading to privacy, compliance, or operational surprises from network activity and retained browsing history.
The manual trigger phrases are broad enough to match ordinary user conversation such as asking for general updates, which can cause the skill to run unexpectedly. Because this skill performs external network access and writes persistent state files, accidental invocation can trigger unintended data collection, outbound requests, and file modifications without clear user intent.
No suspicious patterns detected.
