evidence-driven

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to ingest and act upon data from local project files such as DESIGN.md and blueprints, which creates an indirect prompt injection surface.
  • Ingestion points: Blueprint files, DESIGN.md, and task descriptions.
  • Boundary markers: Absent; the instructions do not define delimiters to separate untrusted content from the system prompt.
  • Capability inventory: The agent is authorized to perform file system writes and execute shell commands (specifically for running test suites).
  • Sanitization: No mechanisms for sanitizing or validating the content of ingested files are specified.
  • [NO_CODE]: The skill consists exclusively of markdown-based methodology guides and instructions. It does not include executable scripts, binaries, or configuration files that run code independently.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 02:48 AM