RAP Sheet home
Install the bug reporting skill
Its theme's rank, 14 days: 2 on the Claude Code sheet
6 people reported

All time, since Oct 17.

Pentest work blocked

Reporters say a sanctioned pentest, approved by the client or against a test work target, is blocked.

Is this your bug? What gets counted gets fixed. Pile on.

Paste this into your agent. It files your report, with your error and version.

I hit this bug: rapsheet.dev/sheets/claude-code/issues/18834/file
Follow it to file my report. Show me the text before you send.

No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends

Growing. 3 reports in the last 7 days and 1 the week before. Not fixed, and no vendor reply yet.

Authorized penetration testing work gets blocked or refused.

Is this your bug?

File my report
Where
Security task handling
Versions
2.1.302 to 2.1.319. Still reported on the newest version, 2.1.319.
Platforms
Linux, macOS, Windows
How bad
Breaks a normal workflow. Some reports say it blocks them completely.

Part of: Safeguards block session requests34 bugs

  1. Cyber safeguard blocks sessions377 people
  2. Reasoning_extraction safeguard block134 people
  3. Cyber safeguard pauses sessions52 people
  4. Safeguards refuse work requests48 people
  5. Safeguards block requests47 people
  6. Classifier halts routine replies12 people
  7. Requests blocked with a [cyber] flag8 people
  8. Refusal on own-code hardening11 people
  9. SSH to own devices refused7 people
  10. CTF requests flagged as malicious6 people
Show all 33Show only the largest 10
  1. Classifier blocks own-project work6 people
  2. Classifier halts reverse engineering5 people
  3. Safeguards flag verified cyber work6 people
  4. Firmware requests flagged as cyber6 people
  5. Classifier stops benign replies5 people
  6. reasoning_extraction API error5 people
  7. Safeguard blocks all messages4 people
  8. [bio] classifier blocks responses4 people
  9. Reasoning extraction safeguard block4 people
  10. Security investigation requests blocked3 people
  11. Classifier stops DeFi bot work3 people
  12. Safeguards block CVP members3 people
  13. "[cyber]" flag stops sessions1 person
  14. Safety classifier blocks agent3 people
  15. Fictional hacking content flagged3 people
  16. Cyber verification prompt recurs2 people
  17. Cyber safeguards block own devices2 people
  18. Safety classifier stops auth work2 people
  19. Phishing research project flagged2 people
  20. Cyber stop on report tasks2 people
  21. Cyber safety block on audits2 people
  22. Biological safeguard triggers in sessions with no biology content2 people
  23. Unexpected safeguards notice2 people

Original reports6, newest first

  1. Refuses authorized penetration testing requests#108020
  2. Overly restrictive refusals for authorized security research#107143
  3. Claude Code blocks authorized penetration testing work#106773
  4. Incorrectly blocks authorized pentest against test target#105363
  5. Classifier blocks authorized pentest response mid-output#104176
  6. Claude Code refuses or errors when running sanctioned penetration testing tasks#102991

Do you work on Claude Code?

Claim its RAP Sheet to see what your users report and answer them in one place.

Claim a tool