docs: add Static Analysis Complement to ASI mapping#179
Open
ppcvote wants to merge 1 commit into
Open
Conversation
Maps 12 static prompt defense vectors to ASI01–ASI10 controls with production gap rates from 1,589 real-world system prompts. Establishes the correlation layer between pre-deployment defense posture (static) and runtime detection (SINT PolicyGateway). Key data: - 78.3% of prompts score F on static defense audit - 97.9% lack indirect injection defense - 97.2% lack unicode attack defense - 93.8% lack role boundary enforcement Cross-references: UltraProbe, Cisco MCP Scanner (PR sint-ai#146), Microsoft Agent Governance (PR #854), Guardrails AI Hub validator, HeadyZhang/agent-audit. Ref: HeadyZhang/agent-audit#5 Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a Static Analysis Complement section to
docs/conformance/owasp-asi-mapping.md, establishing the correlation between pre-deployment prompt defense posture and SINT's runtime security enforcement.Placement
After the existing "Known Gaps" section, before "Certification Notes" — as requested by @pshkv in HeadyZhang/agent-audit#5.
Key data points
What this enables
SINT fixture attack payloads (e.g.,
ASI01-attack-role-override-you-are-now) can now serve as regression seeds for static defense calibration. When a prompt scores 0/100 statically, these attacks should succeed at a higher rate than when the prompt scores 90/100 — creating a measurable correlation between the two layers.Ref: HeadyZhang/agent-audit#5
🤖 Generated with Claude Code