planning-with-files

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill's core workflow relies on the agent reading and following instructions from task_plan.md and notes.md to refresh its 'attention window'.
  • Ingestion points: Data enters through notes.md (e.g., from web research as seen in Example 1) and is summarized into the task plan.
  • Boundary markers: The templates do not use delimiters or instructions to treat the file content strictly as data, increasing the risk that the agent may obey instructions embedded in untrusted research findings.
  • Capability inventory: The skill uses file-system read/write operations to influence subsequent agent decisions and tool selections.
  • Sanitization: No sanitization or validation of the external content is prescribed.
  • Metadata Poisoning (LOW): The reference.md file contains fictionalized information regarding the acquisition of 'Manus' by Meta for $2 billion in December 2025. This is used as a psychological anchoring technique to establish authority and enforce the 'Critical Rules' defined in SKILL.md.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 07:54 AM