project-planner

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection during the initial project analysis phase.
  • Ingestion points: The skill explicitly instructs the agent to read and summarize files such as README.md and CLAUDE.md from the user's workspace to establish project scope.
  • Boundary markers: The instructions do not define delimiters or defensive directives to ensure the agent distinguishes between its own task logic and potentially malicious instructions contained within the ingested files.
  • Capability inventory: The agent is granted access to high-impact tools including Write, WebFetch, and task modification tools (TaskCreate, TaskUpdate), providing a means for an injection attack to modify the environment or exfiltrate data.
  • Sanitization: No sanitization, validation, or structural checking is performed on the content retrieved from local codebase documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 08:42 PM