The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill researches individuals and companies by fetching and processing live web data from search engines and specific URLs (e.g., LinkedIn, news sites).
Ingestion points: Web content retrieved via nimble search and nimble extract commands in SKILL.md (Steps 3, 4, 5).
Boundary markers: The skill lacks explicit boundary markers or 'ignore' instructions when processing this external content, which could allow malicious instructions embedded in web pages to influence the agent's briefing synthesis.
Capability inventory: The skill has access to the Bash tool for CLI operations and Write capabilities to modify local memory files.
Sanitization: No explicit sanitization or escaping of external content is defined before interpolation into the agent's context.
[COMMAND_EXECUTION]: The skill heavily utilizes the Bash tool to execute the nimble CLI for data retrieval and python3 for runtime date calculations. While these are core functionalities, they represent significant system capabilities.
[EXTERNAL_DOWNLOADS]: The references/profile-and-onboarding.md file provides instructions for installing the @nimble-way/nimble-cli package via npm. As this is a resource owned by the skill's author (nimbleway), it is documented as a standard vendor dependency.
[CREDENTIALS_UNSAFE]: The onboarding documentation in references/profile-and-onboarding.md suggests that users store their NIMBLE_API_KEY in plain text within shell configuration files (~/.zshrc, ~/.bashrc) to persist the environment variable across sessions.

meeting-prep