The Agent Skills Directory

[NO_CODE]: The skill consists entirely of markdown documentation and reference guides. It does not include any scripts, executables, or instructions for the agent to run code or perform system-level operations.
[SAFE]: A thorough review of all content, including the prioritization frameworks, revealed no evidence of prompt injection, obfuscation, or malicious intent. The skill adheres to its stated purpose of providing a planning framework.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as product backlogs and strategy documents. While this constitutes a data ingestion surface, the skill lacks any capabilities—such as file writing, network access, or shell execution—that could be exploited via malicious instructions embedded in that data.
Ingestion points: Backlog items and strategy goals provided as input in SKILL.md.
Boundary markers: None explicitly defined in the instructions.
Capability inventory: No tools, network operations, or shell commands are invoked or requested in the frontmatter or instructions.
Sanitization: No explicit sanitization or filtering is mentioned for processing the backlog items.

roadmap-planning