2 September 2000
September 1, 2000
The NSA engages in sabotage, much of it against American companies and products. One campaign apparently occurred at about the time when PGP's most serious vulnerability was added.
To understand the whole story requires some background.
In Bruce Schneier's newsletter Crypto-Gram he told us last year about Lew Giles, said to be an NSA saboteur wrecking American privacy products in 1997. Schneier says that according to several sources Giles went from company to company, asking them to destroy the security of their own products, and arranging cover stories to protect them. According to Crypto-Gram sometimes Giles worked directly with engineers, with no managers around. The sabotage was always supposed to look like a mistake.
At about the same time, PGP introduced "key recovery" with the hidden flaw recently covered worldwide, including Schneier's own clear description in Slashdot. Other serious vulnerabilities have been found in the PGP versions released then. For example, just last May PGP was found to generate weak keys on Linux and OpenBSD. The original report in BugTraq says the bug was introduced in version 5.0, released in 1997.
Undoubtedly most security bugs are just bugs. But it's also very possible that some are backdoors.
CNN and Network World detailed how the NSA openly strong arms companies, "leaning on software, switch and router vendors" to make them "add a government-approved back door into network gear." Companies working with the NSA, however unwillingly, include Netscape, Sun, and Microsoft. Chris Tolles of Sun says, "Everyone in Silicon Valley, including us, has to have specific staff -- highly paid experts -- to deal with them." If everyone's dealing with them, are any products secure?
Taher Elgamal, who wrote Netscape's so called "data-recovery plan" as demanded by the spooks, said they didn't have a choice. Exports are about half the income for these businesses. In practice companies need NSA's permission to export security products, except for "export grade" junk. NSA only gives permission if the security is crippled in some way.
Duncan Campbell reported in Interception Capabilities 2000 that NSA succeeded in compromising browsers from both Microsoft and Netscape, as well as Lotus Notes. The browsers' security was openly gutted by NSA's insistence on reducing key sizes to whatever the NSA can easily crack at the time. In the case of Lotus Notes the keys appeared to be longer, but just enough of each key was secretly given to the NSA.
According to Network World the NSA "forced MasterCard International, Inc. to dumb down the Secure Electronic Transaction (SET) credit-card encryption standard." NSA insisted that most of every transaction not be encrypted at all. When someone steals a lot of money using SET we'll know why.
Sabotaging friends and foes isn't new for the NSA. It's life long behavior. In Crypto AG: The NSA's Trojan Whore you'll find the intriguing but very disturbing story of how 50 years ago NSA rigged the crypto systems sold by Crypto AG so that NSA could read the supposedly secret messages. Customers of Crypto AG include embassies, military, banks, and rogue nations such as the Vatican.
We can stop this sabotage if we're willing to do the work. There are some obvious steps. First, we can continue to insist on open source. We all know similar vulnerabilities are in closed source products, but they are almost never found. Would anyone have found these flaws in PGP without reading the code? Second, we have to do security reviews of the code. With PGP most of us believed -- or hoped -- someone else had carefully studied the code. Almost no one has. Third, we need code review support services, extending what Sourceforge gives us. Finally -- and this will be very tough for those of us who write code -- we have to give good security reviewers the same kind of credit open source coders get.
We can do the security reviews, or we can settle for NSA trojans. I'm going to go read some Freenet code.
Doug Porter