customer-card-render

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • External Tooling Installation: The skill documentation recommends installing the uv package manager using bootstrap scripts from astral.sh. This is a common installation pattern for this development tool and originates from its official domain.
  • Untrusted Data Processing: The skill processes user-provided markdown artifacts, which presents a surface for potential indirect prompt injection. 1. Ingestion points: Markdown files are read from the user-specified directory in scripts/generate_cards.py. 2. Boundary markers: The generated YAML slide definitions use double-quoted placeholders in templates to encapsulate dynamic text. 3. Capability inventory: The skill performs local file system operations but does not have network access or subprocess execution capabilities. 4. Sanitization: The yaml_escape function in scripts/generate_cards.py escapes backslashes, double quotes, and newlines to prevent structure breakout in the generated YAML.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:56 AM
Security Audit — agent-trust-hub — customer-card-render