First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
2
Score
67/100
Findings (2)
Detects common jailbreak prompt patterns
bypass safetyRemove 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.
Benign heading "'@openai/agents:*'\n;\n// Verbose logging\n..." followed by dangerous content (category: credential_access)
Never paste tokens, API keys, cookies, environment variables, or config files containing secrets.Ensure section headings accurately reflect the content that follows. Remove headings that could mislead an LLM into treating content differently than intended.
Likely FP if the heading mismatch is due to inconsistent markdown formatting or a benign section title that happens to contain keywords like system or config.