sms
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown documentation and JSON evaluation files. It does not contain any executable scripts (Python, JavaScript, shell) or automated tool definitions.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read external context files such as .agents/product-marketing.md. While these are ingestion points for untrusted data, the skill does not include any capabilities (such as subprocess calls, file-write operations, or network exfiltration) that would execute or process this data in a dangerous manner. No explicit boundary markers or sanitization logic are defined for these inputs.
- [SAFE]: No security threats such as prompt injection, credential harvesting, or obfuscation were found in the provided files.
Audit Metadata