The Agent Skills Directory

[SAFE]: The primary function of the skill is the local management of knowledge repositories (catalogs). All operations are confined to the plugin workspace, and no evidence of suspicious behaviors, network activity, or unauthorized data access was found.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool for routine directory and file management tasks within a specific local path ('cogni-trends/catalogs/'). These operations are consistent with the skill's stated purpose and do not involve untrusted input or elevated privileges.\n- [PROMPT_INJECTION]: While the skill ingests and processes data from pursuit project files (e.g., 'tips-value-model.json'), it incorporates human-in-the-loop validation by requiring explicit user approval before performing any data imports or merges, effectively mitigating risks associated with indirect prompt injection.

trends-catalog