writing-structure-planner

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection when analyzing user-provided writing material.
  • Ingestion points: User content is ingested in SKILL.md (Step 1.1) where the agent is instructed to read everything the user provides.
  • Boundary markers: No boundary markers or instructions to ignore embedded commands are present in the workflow.
  • Capability inventory: The skill directs the agent to create and write to markdown files (writer-structure-material-analysis.md and writer-structure-options.md) as specified in SKILL.md (Steps 1.2 and 2.2).
  • Sanitization: No sanitization or validation of the ingested user material is performed before processing or file creation.
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform file system operations, specifically creating and writing results to local markdown files in the project directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 05:10 PM