The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized command execution were detected. The skill is primarily instructional and contains no executable code or scripts.
[EXTERNAL_DOWNLOADS]: The skill references documentation and original research from McKinsey & Company and ScienceDirect. These are recognized, authoritative sources for business strategy frameworks and do not present a security risk.
[PROMPT_INJECTION]: The skill functions by ingesting and analyzing untrusted organizational data, creating an indirect prompt injection surface.
Ingestion points: Workflow sections in SKILL.md where the agent is prompted to collect strategy memos, org charts, and descriptions of leadership behavior.
Boundary markers: No specific delimiters are mandated for the external data.
Capability inventory: The skill utilizes Read, Grep, WebSearch, and WebFetch tools as specified in the frontmatter configuration.
Sanitization: No technical sanitization of ingested content is specified; however, the skill provides clear operational instructions to exclude sensitive personal and business data from analysis.

mckinsey-7s