The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for a business strategist persona. No malicious patterns such as prompt injection, obfuscation, or data exfiltration attempts were detected.
[NO_CODE]: There are no scripts, command-line executions, or external dependencies included in the skill content.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill defines several templates (Account Expansion Plan, QBR Preparation, Churn Prevention) that would typically be populated with external data from CRMs or customer usage reports (SKILL.md).
Boundary markers: Absent; the templates do not include specific delimiters or warnings to ignore instructions embedded within the account data.
Capability inventory: None. The skill does not define or request any tools, shell access, network capabilities, or file-writing permissions.
Sanitization: Absent; the skill relies on the agent's internal safety filters.
Note: While a surface for indirect prompt injection exists in the data-processing templates, the lack of any actionable capabilities or tools makes the risk negligible.

account-strategist