Security audit
Security checks for vulnerabilities and agentic risk
This skill performs disclosed public podcast-appearance research and writes a local report, with no evidence of hidden execution, credential use, or destructive behavior.
Installers should expect this skill to spend web-search calls, use public web and podcast-index sources, and create a local report file. Provide an anchor fact for the intended guest and avoid using it for sensitive or private outreach plans unless local report persistence is acceptable.
The invocation guidance includes broad natural-language triggers like "research X before outreach," which can overlap with ordinary user requests and cause the skill to run unexpectedly. Because the skill performs multi-source web searches and creates a report, accidental invocation can expand data access and side effects beyond what the user explicitly intended.
The skill instructs the agent to write a local markdown report file, but the top-level description does not clearly disclose this side effect to the user. Hidden file creation can violate user expectations, create unwanted artifacts, and in some environments may expose sensitive research targets or operational intent through local persistence.
