feat(aep): add deny capability decisions and output_taint_labels#6
Merged
Merged
Conversation
Two enhancements to buildAEPEvidence(): 1. New denied_tools parameter: when tools are blocked by policy/firewall, emit CapabilityDecision with decision:"deny" and reason_code:"policy_denied". Previously only "allow" decisions were recorded for tools that actually ran. 2. Map isUntrusted from tool_call event data to output_taint_labels ["external", "user-supplied"] on ActionEvidence. This feeds OAA controls for data exfiltration and taint tracking (AAI06, ISO A.6.2, A.8.3, A.8.5). Addresses wasmagent-ops#3 requirements 2 and 3. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
denied_toolsparameter onbuildAEPEvidence()emitsCapabilityDecisionwithdecision: "deny"for tools blocked by policy/firewall. Previously only "allow" was recorded.isUntrustedflag from tool_call events tooutput_taint_labels: ["external", "user-supplied"]on ActionEvidence, enabling OAA taint tracking controls.Motivation
Addresses wasmagent-ops#3 requirements 2 and 3:
partial → supported(deny + CAP finding)not_evaluated → partial(output taint)not_evaluated → partialnot_evaluated → partialTest plan
trajectoryExport.test.tsstill passesbuildAEPEvidence({ denied_tools: ["bash"] })produces deny CapabilityDecisionisUntrusted: trueproducesoutput_taint_labelsguardrails.deniedToolsset, verify deny decisions in exported AEP🤖 Generated with Claude Code