planning-with-files

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill utilizes a PreToolUse hook to automatically read the first 30 lines of task_plan.md into the agent's context. If the agent is manipulated into writing malicious instructions to this file (e.g., after reading a malicious website), those instructions would be re-injected before every write, edit, or bash command.
  • Ingestion points: task_plan.md (read via cat in SKILL.md hooks).
  • Boundary markers: Absent; the file content is echoed directly into the prompt stream without delimiters.
  • Capability inventory: Bash, Write, Edit, WebFetch, WebSearch.
  • Sanitization: None; the skill reads and injects raw text from the filesystem.
  • [Command Execution] (SAFE): The skill includes internal shell scripts (scripts/init-session.sh and scripts/check-complete.sh) to initialize the planning environment and verify task completion. These scripts use standard system utilities and do not process untrusted external input in an unsafe manner.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:50 PM