skills/oaker-io/wewrite/wewrite-style/Gen Agent Trust Hub

wewrite-style

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run the wewrite CLI and local install.sh scripts for environment setup and style processing. These commands are integral to the skill's functionality for managing user configurations.
  • [PROMPT_INJECTION]: The skill features a style-learning capability (Phase 3) that reads external documents from the {home}/corpus/ directory. This creates a surface for indirect prompt injection where malicious instructions in the documents could affect the agent's behavior.
  • Ingestion points: Document files in {home}/corpus/ used during the Phase 3 onboarding process.
  • Boundary markers: No delimiters or safety instructions are defined to separate user content from system prompts.
  • Capability inventory: The agent is authorized to use Bash, Read, Write, Edit, and Glob tools.
  • Sanitization: The skill does not mention any sanitization or validation of the content within the style corpus files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 08:21 AM
Security Audit — agent-trust-hub — wewrite-style