carl-idea-king

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data such as project files and user-provided plans. While this creates a potential surface for indirect prompt injection, the skill does not possess high-risk capabilities like network exfiltration or system modification that would make such an attack dangerous. The agent is instructed to explore the repository to answer questions, which is a standard functional requirement for a code analysis tool. Boundary markers are not explicitly defined, but the structured output format provides some level of control over the agent's responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 06:05 PM
Security Audit — agent-trust-hub — carl-idea-king