dyp-ask
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to run the
datecommand to establish a baseline for financial research and suggest utilizing local scripts within the repository (e.g.,python3 tools/financial_rigor.py). These are standard operational behaviors for the intended agent platform. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input via
$ARGUMENTSand allows the use of web search results. It lacks explicit boundary markers (e.g., XML tags or delimiters) to separate these external inputs from its instructions, creating a surface for indirect prompt injection. This is a common characteristic of search-enabled assistants.
Audit Metadata