cleveragents/cleveragents-core
4
0
Fork 3
Code Issues 6.0k Pull Requests 115 Actions Packages Projects Releases Wiki Activity

[AUTO-ARCH-16] docs(spec): update prompt injection mitigation to use XML-delimited tags #9566

Closed
HAL9000 wants to merge 1 commits from auto-arch-16/spec-xml-prompt-injection-mitigation into master
pull from: auto-arch-16/spec-xml-prompt-injection-mitigation
merge into: cleveragents:master
Conversation 4 Commits 1 Files Changed 1
+1 -1

1 Commits

Author SHA1 Message Date
HAL9000 3780be48bb docs(spec): update prompt injection mitigation to use XML-delimited tags
CI / push-validation (pull_request) Successful in 24s
Details
CI / helm (pull_request) Successful in 25s
Details
CI / build (pull_request) Successful in 26s
Details
CI / quality (pull_request) Successful in 34s
Details
CI / lint (pull_request) Successful in 45s
Details
CI / security (pull_request) Successful in 1m2s
Details
CI / typecheck (pull_request) Successful in 1m14s
Details
CI / e2e_tests (pull_request) Successful in 3m42s
Details
CI / integration_tests (pull_request) Successful in 4m3s
Details
CI / unit_tests (pull_request) Successful in 5m11s
Details
CI / docker (pull_request) Successful in 58s
Details
CI / coverage (pull_request) Successful in 13m5s
Details
CI / status-check (pull_request) Successful in 2s
Details 
Replace [USER_CONTENT_START]/[USER_CONTENT_END] bracket markers with XML-delimited tags as the canonical approach for prompt injection mitigation in the Strategize phase.

Document the sanitization requirement: escape <, >, & before embedding user content in XML-delimited sections. Note that XML tags prevent injection via forged closing tags when combined with proper sanitization.

Cross-reference _sanitize_xml_content() as the reference implementation.

Closes #9522
 2026-04-14 23:12:39 +00:00