planning-with-files

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill defines a PreToolUse hook that automatically reads the first 30 lines of task_plan.md into the agent's context window before every use of Write, Edit, or Bash tools. This behavior is intended to refresh the agent's goals but creates a vulnerability where malicious instructions within the plan file could influence the execution of the subsequent tool.
  • Ingestion points: SKILL.md (via PreToolUse hook reading task_plan.md from the current working directory).
  • Boundary markers: None. The content of the file is echoed into the context without delimiters or warnings to ignore embedded instructions.
  • Capability inventory: The skill is granted access to high-risk tools including Bash, Write, Edit, and WebFetch in its configuration.
  • Sanitization: None. The file content is read and injected directly without validation or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:10 PM
Security Audit — agent-trust-hub — planning-with-files