First Seen
Feb 18, 2026
Last Scanned
Feb 22, 2026
Findings
2
Score
84/100
Findings (2)
Detects fetching external URLs and using the content as agent instructions or rules
curl "$BASE/rulesSanitize or validate all external inputs (file contents, API responses, user messages) before including them in prompts or tool calls. Implement input/output boundaries between trusted and untrusted data.
Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.
Detects fetching external URLs and using the content as agent instructions or rules
curl -X POST "$BASE/rulesSanitize 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.
Likely FP if the matched text is the skill's own instruction set describing how to handle user input, not an actual injection payload.