bro
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized commands were detected. The skill is restricted to natural language processing and lacks any tool-calling capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes the conversation history. Ingestion points: The agent's last message (referenced in SKILL.md). Boundary markers: Absent. Capability inventory: No capabilities available; the skill is configured with disable-model-invocation: true, preventing the agent from executing tools or code. Sanitization: Absent.
Audit Metadata