web-search
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to check for the presence of
ddgr, install it, and execute searches. - [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the
ddgrutility from well-known public registries like PyPI and Homebrew. - [PROMPT_INJECTION]: The skill describes a workflow that involves fetching and processing untrusted data from the web, which constitutes an indirect prompt injection surface.
- Ingestion points: Search result snippets from
ddgrand full page content retrieved through theWebFetchtool. - Boundary markers: No explicit delimiters or instructions to ignore instructions within fetched data are provided in the skill text.
- Capability inventory: The skill has the ability to execute shell commands (
ddgr) and interacts with other web-fetching capabilities. - Sanitization: The instructions do not include steps for sanitizing or validating content retrieved from the web before processing it.
Audit Metadata