asset-prompt-library
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a prompt template system that interpolates user-provided variable values into a final prompt output. This creates a surface for indirect prompt injection where a malicious actor could provide variable values (via the
--varargument) designed to influence or hijack the behavior of the downstream agent that consumes the generated prompt. - Ingestion points: User input via the
$ARGUMENTSand--varparameters inSKILL.md(e.g., theuseoperation). - Boundary markers: The skill uses Markdown formatting (blockquotes and headers) to structure the output but lacks explicit instructions or delimiters that warn downstream tools to ignore instructions contained within the variable content.
- Capability inventory: The skill utilizes
Read,Write,Edit,Bash,Grep, andGlobtools to manage the template library stored in_docs/asset-prompts/. - Sanitization: There is no evidence of input validation, escaping, or sanitization of user-provided variable values before they are interpolated into the prompt templates.
Audit Metadata