webapp-testing
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted content from web applications.
- Ingestion points: The skill reads HTML content, element text, and browser console logs from arbitrary URLs and local files (described in Approach A and B in
SKILL.md). - Boundary markers: There are no instructions provided to wrap the external web content in delimiters or to ignore potential instructions embedded within the target application's data.
- Capability inventory: The skill allows access to the
Bashtool (frontmatter ofSKILL.md) and provides code templates inSKILL.mdfor executing shell commands viasubprocess.Popento manage local servers. - Sanitization: There is no mention of sanitizing, escaping, or validating the content retrieved from the browser before it is processed by the agent.
Audit Metadata