buyer-persona
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and templates. It contains no executable scripts, shell commands, or binary files.
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by reading external data. 1. Ingestion points: The skill reads
.agents/sales-context.md(SKILL.md). 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to treat this file content as untrusted. 3. Capability inventory: The skill is restricted to text generation and lacks capabilities for file writing, network communication, or command execution. 4. Sanitization: No sanitization or validation of the ingested content is performed. - [SAFE]: No network operations, obfuscation, or persistence mechanisms were detected.
Audit Metadata