grill-me-plus

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists exclusively of markdown instructions in the SKILL.md file and does not include any accompanying scripts, binaries, or configuration files that execute code.
  • [PROMPT_INJECTION]: The skill instructions define an indirect prompt injection surface through the agent's data ingestion logic.
  • Ingestion points: The agent is explicitly instructed to "explore the codebase, files, docs, or current implementation" to answer questions automatically (SKILL.md).
  • Boundary markers: Absent. The instructions do not direct the agent to use delimiters or specific ignore-instruction patterns when reading external files.
  • Capability inventory: The skill utilizes interactive user-input tools (AskUserQuestion, request_user_input) and specifies that the agent should "dispatch a sub-agent" to perform research tasks.
  • Sanitization: Absent. There are no instructions provided to sanitize or validate the content retrieved from project files before it is processed by the agent or sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 07:38 PM
Security Audit — agent-trust-hub — grill-me-plus