find-test-content
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes HTML content from external project pages, creating a potential attack surface for instructions hidden in the data.\n
- Ingestion points: The
scripts/find-block-content.jsscript fetches the HTML of various pages listed in a project'squery-index.jsonto search for block instances.\n - Boundary markers: The
SKILL.mdfile contains an "External Content Safety" section that explicitly warns the agent to treat all fetched content as untrusted and to disregard any embedded commands or directives.\n - Capability inventory: The skill performs network requests using
fetchand logs findings to the console. It does not have capabilities for writing to the filesystem, accessing environment variables, or executing arbitrary system commands.\n - Sanitization: Content is parsed using
jsdomto query the DOM for specific CSS classes, which treats the HTML as data rather than executable content.\n- [COMMAND_EXECUTION]: The skill relies on the execution of a provided Node.js script (scripts/find-block-content.js) to perform its search logic.
Audit Metadata