subject-line-generator
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and formatting templates. It does not perform any shell command execution, file system modifications, or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content such as email bodies and persona context. While this represents a potential ingestion point for untrusted data, the skill lacks any capabilities (such as file-writing or network tools) that could be exploited via embedded instructions.
- [DATA_EXFILTRATION]: No mechanisms for data transfer or external communication are present in the instructions.
- [PROMPT_INJECTION]: There are no patterns indicative of attempts to bypass safety filters, override system instructions, or extract underlying model prompts.
Audit Metadata