before-backend-dev

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill directs the agent to read and incorporate guidelines from local files into its development workflow. 1. Ingestion points: Documentation files located in .trellis/spec/backend/ are read into the agent context. 2. Boundary markers: Absent. The skill does not provide delimiters to distinguish the guidelines from system instructions. 3. Capability inventory: The agent is expected to perform backend development based on these guidelines, which likely involves high-privilege operations like writing code or executing tests. 4. Sanitization: Absent. The skill does not verify or sanitize the content of the guideline files, allowing for potential instruction override if the repository is compromised.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 12:00 AM