The Agent Skills Directory

[SAFE]: The skill follows security best practices by explicitly instructing the agent to treat all user-provided materials and claims as hypotheses rather than facts. This design significantly reduces the risk of the agent being misled by indirect prompt injections contained within external project documents or landing pages.
[SAFE]: The skill's access to local project files is scoped to specified methodology reference directories and user-provided project context, which is consistent with its primary purpose of conducting market research.
[SAFE]: Network operations described in the 'Deep Mode' are restricted to market research activities such as identifying competitors and mining public customer reviews. These actions are performed through the agent's existing tools and do not involve exfiltration of sensitive credentials or unauthorized system access.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation attempts were found in the instructions or the accompanying glossary file.

nmt-market-research