grill-with-docs

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists exclusively of markdown documentation and YAML configuration. No scripts or executable files are present.
  • [SAFE]: No indicators of malicious activity or data exfiltration were detected.
  • [PROMPT_INJECTION]: The skill facilitates an interview process that ingests untrusted design data, creating a potential surface for indirect prompt injection. 1. Ingestion points: User input during the grilling session defined in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill body in SKILL.md implies the creation of Architecture Decision Records (ADR) and glossaries. 4. Sanitization: No specific sanitization or escaping of user-provided content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 10:24 AM
Security Audit — agent-trust-hub — grill-with-docs