Anthropic API key: format and detection

What it is

The key authenticates calls to the Anthropic API. Maskflare's Credentials pack has one detector for standard API keys and a second for admin keys (sk-ant-admin01- with the same body length), both masked by default.

In Maskflare this is the detector anthropic_api_key, labelled "Anthropic API key", category password or access key, in the Credentials pack.

Format

• The literal prefix sk-ant-api03-.
• 93 characters from letters, digits, underscore and hyphen.
• The two letters AA at the end.
• 108 characters in total.

How Maskflare recognises it

No check digit and no entropy floor: the distinctive prefix, the fixed body length and the AA ending are enough to avoid false matches.

A text without sk-ant-api03 is skipped by the keyword prefilter.

Why this page shows no sample key

A realistic sample key would look like a live credential to secret scanners and to anyone skimming the page, and an obviously fake one would not pass this detector's length and entropy rules. The format above is enough to recognise the key: the prefix, the length and the character set.

Regex and validation caveats

• The pattern wants the key to be followed by a quote, a backtick, whitespace, a semicolon, an escaped newline or the end of the text. A key directly followed by a comma or a closing bracket is therefore not matched by this pattern.
• Only keys with the api03 prefix are matched by this detector. A key with another version prefix would need its own rule.
• A truncated key (for example one cut in a log line) does not match, because the length is fixed.

How to detect it in LLM traffic

These keys reach an assistant through pasted environment files, shell history, SDK setup snippets and CI logs. Coding agents add another route: a key exported in the shell can appear in a tool result or a printed environment, which is why Maskflare masks tool inputs and outputs as well as the user's prompt.

Maskflare reads the whole request body, including the system prompt, earlier messages and tool arguments, and replaces each match with a token such as mf_mask_d7e0 before the request goes out. Coding agents are covered through hooks that mask tool inputs and results, so a key printed by a shell command does not travel onward in the next prompt. On ChatGPT, browser protection blocks prompts that contain API keys, tokens or private keys outright.

If you build the detection yourself

1. Scan the raw text rather than parsed fields: keys sit in code, JSON strings, headers, shell output and pasted logs, often with no label at all.
2. Match the prefix and the exact length for the Anthropic API key. Where the key has no fixed prefix, require the provider's name and an assignment next to the value instead of matching any long string.
3. Compute the Shannon entropy of the candidate and reject low values, and keep an allow list of placeholders (${KEY}, repeated characters, the alphabet run), because documentation and templates are full of them.
4. Mask the value before the text is sent anywhere. If the key was already sent, treat it as exposed and rotate it; masking later does not recall it.

How Maskflare handles it

• Protect now, Finance - Protect now, Healthcare, Developer and Monitor first: mask (a reversible token).

The available actions are mask (reversible token), redact, partial, hash, format-preserving encryption, generalize, alert and block. Masked values are kept encrypted for 30 days so that answers can be restored, then they expire; prompts and responses are not logged. The full list of detectors is in the detector reference.

Compliance profiles that include it

All 6 compliance profiles include the Credentials pack, and applying them turns this detector on: HIPAA Safe Harbor, GDPR - EU/EEA, UK GDPR, PCI DSS, US personal data and Switzerland - nDSG health data. A profile is a floor: it never turns anything off or weakens a rule that is already stricter.