Skills
▥NYC
skills/fluid-tools/claude-skills/planning-with-files/Gen Agent Trust Hub

planning-with-files

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (LOW): Indirect Prompt Injection Surface.
  • Ingestion points: The workflow (specifically in examples.md and SKILL.md) directs the agent to perform web searches and store results directly into notes.md.
  • Boundary markers: Absent. The provided templates for notes.md and task_plan.md do not include delimiters or instructions for the agent to ignore potential commands embedded within retrieved external content.
  • Capability inventory: The agent uses WebSearch, Write, Read, and Edit tool capabilities to interact with these files.
  • Sanitization: Absent. There are no instructions to sanitize, escape, or validate content retrieved from external sources before it is incorporated into the persistent file-based memory.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:01 PM