The Agent Skills Directory

[SAFE]: No malicious code, obfuscation, or dangerous execution methods were detected. The skill consists of markdown-based instructions, job personas, and document templates for product management workflows.
[PROMPT_INJECTION]: The skill contains an ingestion point for indirect prompt injection through its intervention mechanism. Ingestion points: The agent is instructed to read content from files located in the human-interventions/active/ directory. Boundary markers: No delimiters or safety instructions are provided to separate user-supplied intervention content from the agent's core instructions. Capability inventory: The skill is limited to document generation and workflow progression; it does not list or utilize tools for network exfiltration, shell command execution, or sensitive file access. Sanitization: There is no mention of sanitizing or validating the content of intervention files before the agent processes and integrates them.

product-discovery