redaction-guard Skill
Use whenever you are about to emit operator-visible content — a chat/thread message, a PagerDuty or ServiceNow note, a commit message or pull-request body, or any report artifact (HTML, PowerPoint, Teams card). Deterministically masks secrets, credentials, tokens, private keys, URI-embedded passwords, and PII so they n Published by microsoft in sre-agent.
What is redaction-guard Skill?
Use whenever you are about to emit operator-visible content — a chat/thread message, a PagerDuty or ServiceNow note, a commit message or pull-request body, or any report artifact (HTML, PowerPoint, Teams card). Deterministically masks secrets, credentials, tokens, private keys, URI-embedded passwords, and PII so they n Published by microsoft in sre-agent. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Documentation
- Documentation use cases
Technical details
- Install or run with Copy skill directory
When to use redaction-guard Skill
- Use it for documentation.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/sre-agent
- Skill file: labs/zava-learning/sre-config/agent-config/skills/redaction-guard/SKILL.md
What it does
Use whenever you are about to emit operator-visible content — a chat/thread message, a PagerDuty or ServiceNow note, a commit message or pull-request body, or any report artifact (HTML, PowerPoint, Teams card). Deterministically masks secrets, credentials, tokens, private keys, URI-embedded passwords, and PII so they n
Skill instructions
Zava Learning — Redaction Guard A cross-cutting safety layer: nothing sensitive ever reaches an operator-visible surface. The triggering alert is symptom-only and the investigation touches Key Vault secrets, connection strings, access tokens and learner PII — none of which may be exposed in chat, notes, PRs, or reports. Load the standard, then scrub Retrieve the canonical policy and scrubber with SearchMemory("zava-redaction"). It defines what counts as sensitive, the credential files you must never print, and a deterministic redact() function. Apply redact() (via ExecutePythonCode) to every string you are about to emit — chat summary, note body, PR/commit text, and the assembled HTML/markdown/deck — before it leaves the agent. The scrubber is idempotent, so running it more than once is safe. What to redact (summary — see zava-redaction for the full list) - Secrets & credentials: passwords, PGPASSWORD, connection strings, Key Vault secret values, client secrets, API / access / account
Explore related resources
Frequently asked questions
What is redaction-guard?
redaction-guard is a open-source AI agent skill with Copy skill directory. Use whenever you are about to emit operator-visible content — a chat/thread message, a PagerDuty or ServiceNow note, a commit message or pull-request body, or any report artifact (HTML, PowerPoint, Teams.
Who is redaction-guard best for?
redaction-guard is best for reusing agent instructions, scripts, and references, documentation workflows.
How do I install redaction-guard?
Install or run redaction-guard using Copy skill directory. Check redaction-guard for the latest setup command.
Is redaction-guard actively maintained?
redaction-guard may need a closer maintenance check before production use.
Auto-fetched from GitHub.
