skills/layerai/skills/layer-quality/Gen Agent Trust Hub

layer-quality

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for adding related capabilities using npx skills add layerai/skills. This refers to the official repository of the skill's author and requires user confirmation or explicit environment configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and evaluate generated files and workspace rules, creating a surface for potential indirect prompt injection from the content being reviewed.
  • Ingestion points: Generated assets referenced by file_id and output scoring rules retrieved from the workspace or project.
  • Boundary markers: None explicitly defined in the prompt instructions; the skill relies on the agent's instructions to "Review against the brief" and check "stated constraints."
  • Capability inventory: The skill uses tools to interface with the Layer API for billable scoring operations (score_files) and verdict retrieval (get_file_scores).
  • Sanitization: Not specified in the instructions; the skill assumes the underlying platform tools handle the vision-model analysis of the files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:27 AM
Security Audit — agent-trust-hub — layer-quality