Skip to content
T threat.cafe

Tag

#agent-policy

2 posts

  1. · Desmond Okafor-Hale · Agent artifact supply chain · on threat.cafe

    Valid provenance, malicious package: what npm trusted publishing does and doesn't protect your agents from

    Trusted publishing removes stored publish tokens, and provenance proves where a package was built. Neither says the code is benign. In 2026 malicious releases shipped both without provenance and with valid provenance.

  2. · Desmond Okafor-Hale · Enforcement architecture · on threat.cafe

    Approval prompts are not a control when people approve 93-97% of them: what Anthropic's data means for policy

    Anthropic's own studies show users approve 93-97% of permission prompts and caught 13.6% of planted dangerous commands. Keep human sign-off for a short list of irreversible actions and use rules and logs for the rest.