docs-writer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis

Indirect Prompt Injection: The skill is designed to ingest and process documentation and code files from the repository. If these files contain adversarial instructions, they could potentially influence the agent's output or actions. This risk is inherent to skills that handle external data.

Command Execution: To maintain project standards, the skill utilizes npm install and npm run format. These commands execute scripts based on the project's local configuration. The skill correctly incorporates a step to seek user confirmation before running these commands.

Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:31 AM
Security Audit — agent-trust-hub — docs-writer