+- Arpan Sharma \<https://github.com/Arpan0995\> - initial audit of BCPQC provider consistency starting with HQC, which led to the exposure of a number of issues in the JCA provider service interfaces for other BCPQC algorithms. In-depth auditing of PQC signature algorithms in the provider leading to the correction of a number of JCA API compliance issues. Initial implementation of the guard that lets a signature context be set on the composite ML-DSA services before initSign / initVerify, the composite counterpart of the base-engine fix for issue #2396 (issue #2412). Audit of the LMS / HSS stateful private key decoder, establishing that the level count, the one-time index and the persisted tree cache were all accepted without validation (issue #2414); that issue was also the inspiration for the further investigation which found the HSS and XMSS^MT decoders accepting a private key whose declared index disagreed with the traversal state stored beside it, allowing a one-time key to be used twice. Audit of the high-level OpenPGP API (org.bouncycastle.openpgp, org.bouncycastle.openpgp.api) and the bcpg packet layer beneath it, spanning certificate evaluation, message verification, decryption and signature subpacket parsing, which found certificates being used without the certifications RFC 9580 requires of them, malformed but signed content reaching ordinary reader code as unchecked exceptions, a truncated message being read as a clean end of message, and unverified plaintext being released ahead of the integrity check (issues #2417, #2424, #2426). Audit of the recipient side of the CMS RFC 9629 KEMRecipientInfo path, which found three sender-controlled fields leaving methods declared to throw CMSException as unchecked exceptions and the kekLength never being confirmed against the wrap algorithm, and which led to the same translation being added to the neighbouring AuthEnvelopedData constructor and the two streaming parsers (issue #2422). Audit of RSA-PSS parameter handling in the provider, which found Signature.setParameter reporting a rejected trailer field as an unchecked exception and leaving the rejected spec half-applied, so that the parameters reported for a signature were not the ones it had been made with (issue #2421). Audit of the PKCS#12 key store entry-setting boundary, which found setKeyEntry reporting a certificate whose public key the provider cannot resolve as an unchecked exception rather than the KeyStoreException it declares, and which led to the same guard being applied to setCertificateEntry and to the RFC 9579 PBMAC1 store, and to the rejected entry no longer being left behind in the store (issue #2419). Further auditing of the verification and expiration paths of the high-level OpenPGP API, which found a configured algorithm policy not being applied to inline message verification, an expired primary key still offering its subkeys, and a data signature being reported valid past its own expiration time. CMS SignedData and PKIX certification path test coverage for the eighteen Composite ML-DSA parameter sets, which had been reachable through the CMS and cert-path signature algorithm finders with no test exercising either (PR #2437). Identification and fix of the output offset in the AEAD stream cipher data operator that made Grain-128AEAD return corrupted plaintext from a decryption driven in chunks, with the streamed decryption coverage that had been missing (PR #2447). Identification and fix of the RFC 9709 content-encryption algorithm being left wrapped at the CMS recipient key-size, allowed-algorithm and tag-size checks, so that none of them applied to the algorithm the content was encrypted under (PR #2446). Identification and fix of the YubiKey OpenPGP smart-card decryptor factories zeroizing the user PIN array belonging to the KeyPassphraseProvider that supplied it, which left the next private-key operation presenting an all-zero PIN to the card (PR #2444). Identification and fix of the TupleHash element length prefix being computed in int arithmetic, which left an element of 2^28 bytes or more either not returning from the length encoding loop or carrying the prefix of an empty element, and of the same loop not returning on a negative output length (PR #2462). Identification and fix of the ITS explicit certificate builder choosing the certificate's signature type from the verification key indicator rather than the signing key's curve, which mislabelled brainpoolP256r1 signatures and implicit-issuer P-256 signatures and left brainpoolP384r1 keys unable to sign a certificate (PR #2463).
0 commit comments