skills/react/react/plan-update/Gen Agent Trust Hub

plan-update

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior detected. The skill provides a workflow for automating documentation updates within a compiler development environment. All file access is restricted to local documentation and source paths appropriate for the developer context.
  • [PROMPT_INJECTION]: The skill uses input from the user ($ARGUMENTS) and content from local plan documents to construct instructions for subagents. While this creates an indirect prompt injection surface, it is a standard pattern for the skill's primary purpose. 1. Ingestion points: User-supplied topic in $ARGUMENTS and the plan document text at . 2. Boundary markers: The subagent prompt template uses double quotes to wrap the injected topic. 3. Capability inventory: The skill reads local filesystem paths and launches secondary analysis agents. 4. Sanitization: No explicit output sanitization or instructions to ignore embedded prompts are present in the orchestrator.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 07:35 PM