performance-audit
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external websites, which could potentially contain malicious instructions aimed at the agent.
- Ingestion points: The skill uses
browser-devtools-clito fetch console messages, network request data, and screenshots from external URLs provided by the user (as seen inSKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content in the logs it retrieves.
- Capability inventory: The skill has access to shell commands via
browser-devtools-cliandnode-devtools-cli, including the ability to connect to and trace local processes via PID. - Sanitization: There is no evidence of sanitization for the retrieved log messages or network data before they are processed by the agent.
Audit Metadata