Re:Claude Cowork Exfiltrates Files
by ptx on Wednesday January 14, 2026 @05:16PM
(#46624511)
This is like trying to fix SQL injection by limiting the permissions of the database user instead of using parameterized queries (for which there is no equivalent with LLMs). It doesn't solve the problem.
[ Parent
| on HN ]
It also has no effect on whole classes of vulnerabilities which don't rely on unusual writes, where the system (SQL or LLM) is expected to execute some logic and yield a result, and the attacker forces a different logic path.
Using the SQL analogy, suppose this is intended:
SELECT hash('letmein') == secretfiles.hashed_access_code FROM secretfiles WHERE secretfiles.id = '123';
SELECT hash('') == hash('') -- ') == secretfiles.hashed_access_code FROM secretfiles WHERE secretfiles.id = '123';