First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
2
Score
67/100
Findings (2)
Detects attempts to override or ignore previous instructions
ignore previous instructionsRemove the injection payload from the skill definition. Text that attempts to reset agent context or override prior directives is a direct attack vector.
Likely FP if the text is in a security tutorial or research paper discussing injection techniques as examples, not in an active skill description.
Benign heading "'@openai/agents:*'\n;\n// Verbose logging\n..." followed by dangerous content (category: credential_access)
Instruction override: "ignore previous instructions", "disregard above", "you are now", "new system prompt"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.