6 people reported
All time, since Sep 23, including 2 thumbs-up on GitHub.
Classifier blocks own-project work
“Since moving to Opus 5.5, the safety / auto-mode classifier has blocked two ordinary pieces of work.”
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/3315/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
Safety classifier stops sessions on first-party development work. Responses stop with "Opus 5.5's safeguards flagged this session" while reading own files, memory notes or public research.
Is this your bug?
File my report- Where
- safety classifier
- Error text
Opus 5.5's safeguards flagged this session (https://www.anthropic.com/legal/aup).- Versions
- 2.1.281 to 2.1.301
- Platforms
- macOS
- How bad
- Stops work: a core feature can't be used. Some reports say it used to work. Some reports say it blocks them completely.
Part of: Safeguards block session requests34 bugs
- Cyber safeguard blocks sessions377 people
- Reasoning_extraction safeguard block134 people
- Cyber safeguard pauses sessions52 people
- Safeguards refuse work requests48 people
- Safeguards block requests47 people
- Classifier halts routine replies12 people
- Requests blocked with a [cyber] flag8 people
- Refusal on own-code hardening11 people
- SSH to own devices refused7 people
- Pentest work blocked6 people
Show all 33Show only the largest 10
- CTF requests flagged as malicious6 people
- Classifier halts reverse engineering5 people
- Safeguards flag verified cyber work6 people
- Firmware requests flagged as cyber6 people
- Classifier stops benign replies5 people
- reasoning_extraction API error5 people
- Safeguard blocks all messages4 people
- [bio] classifier blocks responses4 people
- Reasoning extraction safeguard block4 people
- Security investigation requests blocked3 people
- Classifier stops DeFi bot work3 people
- Safeguards block CVP members3 people
- "[cyber]" flag stops sessions1 person
- Safety classifier blocks agent3 people
- Fictional hacking content flagged3 people
- Cyber verification prompt recurs2 people
- Cyber safeguards block own devices2 people
- Safety classifier stops auth work2 people
- Phishing research project flagged2 people
- Cyber stop on report tasks2 people
- Cyber safety block on audits2 people
- Biological safeguard triggers in sessions with no biology content2 people
- Unexpected safeguards notice2 people
Not quite your bug?
- Unauthorized edits despite rules14 people
Original reports5, newest first
- OPUS 5.5 - Refusal to build simple NextJS app w/o reason given#104130
- safety classifier is *extremely* sensitive and impedes much of my work#101738
- 5.5 safeguards stop sessions on authorized first-party work: reading own files, own memory notes (Bedrock, no private feedback path)#98724
- Opus 5.5: classifier blocks ordinary work (public research, own-machine scripts), and loses track early in short sessions#96589
- Opus 5.5: classifier blocks ordinary work (public research, own-machine scripts), and loses track early in short sessions#96572