design-principles

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface by design, as it ingests untrusted data from the local environment.
  • Ingestion points: The skill reads all files within the context/ directory, as well as design-principles.md and context/sprint-roles.md, to establish background context for the session.
  • Boundary markers: There are no specified delimiters or instructions to ignore embedded commands when the AI reads and interprets these external files.
  • Capability inventory: The skill's capabilities are limited to reading and writing text-based files within the local working directory; it lacks network access, shell command execution, or system-level privileges.
  • Sanitization: The skill does not perform any validation or filtering of the content retrieved from the context/ folder before incorporating it into its reasoning process.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 03:25 AM