Repository navigation
Conversation
…ess, reconcile narrative (usestrix#322) Three related gaps let authorized findings slip through a headless scan: 1. Credentials/tech hints passed via --instruction were treated as background, so the agent gave up at a 401 instead of driving the login flow. Add an operational principle that provided credentials and technology hints MUST be used to authenticate before concluding anything about the authenticated surface, with the login request/response as evidence either way. 2. Demonstrated unauthenticated access (e.g. an open Docker Registry serving GET /v2/_catalog and image pull/push) was dismissed as "configuration hygiene". Carve out in both the system prompt and the severity-calibration skill: the bare absence of an auth header is an observation, but proven anonymous access to a protected operation or data is a reportable finding scored on the access it grants, with missing auth as an aggravating factor. 3. A report narrative could describe weaknesses while the vulnerability count stayed zero. Add _narrative_reconciliation to finish_scan: a zero-finding report whose prose contains weakness language rides back a narrative_warning so the contradiction is visible in the run record, plus a reconciliation gate in the finish_scan docstring. Tests cover the narrative-reconciliation helper.
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
…ess, reconcile narrative (#322)
Three related gaps let authorized findings slip through a headless scan:
Credentials/tech hints passed via --instruction were treated as background, so the agent gave up at a 401 instead of driving the login flow. Add an operational principle that provided credentials and technology hints MUST be used to authenticate before concluding anything about the authenticated surface, with the login request/response as evidence either way.
Demonstrated unauthenticated access (e.g. an open Docker Registry serving GET /v2/_catalog and image pull/push) was dismissed as "configuration hygiene". Carve out in both the system prompt and the severity-calibration skill: the bare absence of an auth header is an observation, but proven anonymous access to a protected operation or data is a reportable finding scored on the access it grants, with missing auth as an aggravating factor.
A report narrative could describe weaknesses while the vulnerability count stayed zero. Add _narrative_reconciliation to finish_scan: a zero-finding report whose prose contains weakness language rides back a narrative_warning so the contradiction is visible in the run record, plus a reconciliation gate in the finish_scan docstring.
Tests cover the narrative-reconciliation helper.