Write A Prd
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill is coherent for drafting a PRD, but users should review before letting it read a repository or create a GitHub issue.
This skill appears safe and purpose-aligned as an instruction-only PRD helper. Before using it, make sure the repository contents can be inspected by the agent and review the final PRD before allowing it to create a GitHub issue.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may read project files while preparing the PRD.
The skill asks the agent to inspect the repository. This is expected for a PRD/codebase planning workflow, but repository contents may be sensitive and should stay scoped to the relevant project.
Explore the repo to verify their assertions and understand the current state of the codebase.
Use it only in repositories you are comfortable having the agent inspect, and direct it to the relevant areas of the codebase.
The skill may create an issue under the user's GitHub permissions, potentially visible to collaborators or the public depending on the repository.
Creating a GitHub issue uses repository/account authority and may publish or persist the PRD in the repository issue tracker. This is disclosed and purpose-aligned, but it is still a user-visible account action.
The PRD should be submitted as a GitHub issue.
Review the PRD content and target repository before approving issue creation.