First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
3
Score
42/100
Findings (3)
Detects common jailbreak prompt patterns
Developer Mode Remove directives that attempt to exfiltrate data through the agent's response (e.g., asking the agent to embed credentials in URLs or include secret values in output).
Likely FP if the text is a legitimate tool instruction about displaying configuration to the user (e.g., show current settings) without external transmission.
Detects common jailbreak prompt patterns
Developer Mode Remove directives that attempt to exfiltrate data through the agent's response (e.g., asking the agent to embed credentials in URLs or include secret values in output).
Likely FP if the text is a legitimate tool instruction about displaying configuration to the user (e.g., show current settings) without external transmission.
Detects automatic registration of MCP servers into agent configuration
claude mcp add Pin the curl/wget download to a specific URL with version and verify the downloaded file's SHA-256 checksum before using it. Prefer package manager installs over raw downloads.
Likely FP if the download is from a well-known canonical source (e.g., official GitHub release) and the documentation includes checksum verification steps.