The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill is purely instructional and provides templates for product management research activities.\n- [NO_CODE]: The skill contains only Markdown documentation and templates. It does not include any scripts, binary files, or external dependencies, eliminating risks associated with code execution or supply chain attacks.\n- [PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass AI safety guardrails or override system prompts. The use of "IMPORTANT" and structural headers is consistent with standard instructional formatting.\n- [DATA_EXFILTRATION]: There are no network-related commands (curl, wget) or references to external domains that would facilitate data exfiltration. All references are to local markdown files within the skill folder.\n- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external data (interview transcripts), it does not possess any dangerous capabilities (such as file writes, shell execution, or network access) that could be exploited through malicious content in those transcripts. The ingestion points are purely for summarization and synthesis within the AI's context window.

research-expert