The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access behaviors were detected. The skill is primarily instructional and operates within a defined strategic context.
[NO_CODE]: The skill consists entirely of Markdown instructions, workflows, and templates. It does not include scripts, binaries, or commands that could be executed by the agent or the underlying system.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external documents such as client briefs, research notes, and contracts.
Ingestion points: Workflow inputs include 'Pricing And Packaging Strategy brief', 'Claims, assumptions, and supporting evidence', and 'signed contracts' (SKILL.md).
Boundary markers: The skill does not define specific delimiters for these inputs, but instructs the agent to 'separate known facts from assumptions'.
Capability inventory: The skill is restricted to 'read-only' operations to produce drafts or reviews; it has no capabilities for network exfiltration or command execution.
Sanitization: No explicit sanitization or filtering of input data is mentioned, but the lack of powerful capabilities limits the potential impact of any injected instructions.

saas-pricing-and-packaging-strategy