secondme-prd

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill updates the .secondme/state.json configuration file with content derived from user dialogue.
  • Ingestion points: User input collected via the AskUserQuestion tool and existing data within the .secondme/state.json file.
  • Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions embedded within the user-provided text.
  • Capability inventory: File system modification access specifically for the .secondme/state.json file.
  • Sanitization: Absent; user-provided descriptions for goals, users, and features are directly written into the JSON structure without filtering.
  • Risk Context: While the skill's primary function is state management, the lack of sanitization allows for potential injection into a file that downstream tools (such as the mentioned /secondme-nextjs code generator) may process, potentially leading to unintended behaviors in subsequent steps.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 10:25 PM