The Agent Skills Directory

[SAFE]: The skill is entirely composed of markdown documentation providing methodology for brand research and contains no executable files or configurations.
[NO_CODE]: No code, scripts, or external software dependencies are defined or utilized in this skill.
[INDIRECT_PROMPT_INJECTION]: The skill instructions include gathering and reading various external documents such as mission statements and annual reports. While this creates a surface for untrusted data ingestion, the skill lacks any associated high-risk capabilities (like shell access or network exfiltration) that would allow an injection to cause harm.
Ingestion points: Baseline information to request section in SKILL.md.
Boundary markers: Absent.
Capability inventory: None (no tools or scripts provided).
Sanitization: Absent.

conducting-research