First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
3
Score
92/100
Findings (3)
Detects attempts to make the AI assume a different role
you are now a verifiedRemove directives that attempt to alter the agent's behavior or persona. Skill descriptions should describe tool functionality, not contain behavioral commands for the agent.
Likely FP if the matched text is part of the skill's legitimate system prompt configuration that defines the tool's behavior for the user, not an attack.
Detects MCP server configurations connecting to non-localhost remote URLs
"url": "https://github.com/myproject/repo"Change the MCP server URL to localhost or a trusted internal endpoint. If a remote server is required, verify the domain ownership and use HTTPS with certificate validation.
Likely FP if the URL points to example.com, a documentation domain, or a well-known SaaS API endpoint (e.g., api.openai.com).
Detects MCP server configurations connecting to non-localhost remote URLs
"url": "https://github.com/Uniswap/v4-core"Change the MCP server URL to localhost or a trusted internal endpoint. If a remote server is required, verify the domain ownership and use HTTPS with certificate validation.
Likely FP if the URL points to example.com, a documentation domain, or a well-known SaaS API endpoint (e.g., api.openai.com).