grilling-designs

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to perform design interviews and stress-test plans. It functions by asking iterative questions and referencing repository content such as documentation, source code, and configuration files to build a shared understanding.
  • [PROMPT_INJECTION]: The instructions involve reading data from the local repository, creating a surface for indirect prompt injection. However, the skill lacks high-risk capabilities like network access or arbitrary command execution, which significantly mitigates the potential impact of such an attack.
  • Ingestion points: Repository files, callers, config, docs, and tests as specified in SKILL.md.
  • Boundary markers: Not present.
  • Capability inventory: File reading and searching; no network or execution capabilities.
  • Sanitization: Not present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 11:19 AM
Security Audit — agent-trust-hub — grilling-designs