east-african-english
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for style, tone, and grammar. It does not include scripts, executable code, or commands that interact with the host system.
- [DATA_EXFILTRATION]: No network operations (such as curl or wget) or sensitive file path access (such as .ssh or .aws) were detected in the instructions.
- [PROMPT_INJECTION]: The skill contains no patterns typical of direct prompt injection, such as instructions to override safety filters or disregard previous rules. It defines a narrow scope for stylistic review of proposal text.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data (draft proposal text), but the risk is negligible as the skill lacks exploitable capabilities.
- Ingestion points: Processes 'Draft or planned English text' provided through the proposal workflow as defined in SKILL.md.
- Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are present for the input text.
- Capability inventory: No subprocess calls, execution tools, file writing, or network operations are included in the skill definition.
- Sanitization: No programmatic sanitization is defined as the skill is entirely descriptive.
Audit Metadata