B
85/100 First Seen
Feb 19, 2026
Last Scanned
Feb 20, 2026
Findings
1
Score
85/100
HIGH 1
Findings (1)
HIGH
Fetch URL and use as instructions
L27 Detects fetching external URLs and using the content as agent instructions or rules
prompts from the MCP server FIX
Sanitize or validate all external inputs (file contents, API responses, user messages) before including them in prompts or tool calls. Implement input/output boundaries between trusted and untrusted data.
FP?
Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.