"get secret", "API key", "token"?
request_runtime_secret / request_workload_token
← Skill registry
Agent infrastructurePublic skills
Credentials Management
Secure credential operations — request runtime secrets with scope validation, rotate keys on schedule, revoke on compromise, and audit all access.
What this skill teaches
A reusable playbook for a specific kind of work.
An MCP server tells an agent which actions are available. A skill adds the judgment around those actions: how to recognize the job, which sequence to follow, what to avoid, and how to decide that the result is complete.
Securely manage credentials — list available secrets, request runtime tokens, rotate keys, revoke access, and audit usage. Use when retrieving API keys, rotating secrets, checking credential metadata, auditing access, or validating secret scopes.
Architecture
How Credentials Management guides an ADK-Rust agent.
The skill stays readable and portable because it contains instructions rather than service credentials or business data. ADK-Rust supplies it to the agent, the agent chooses from its reviewed tool boundary, and the connected MCP server performs the authenticated operation.
01
User request
The agent receives a goal expressed in ordinary language.
02
Credentials Management skill
Matches intent, supplies the decision guide, and narrows the tool boundary.
03
ADK-Rust agent
Plans the workflow and streams each meaningful step through the runtime.
04
mcp-credentials-vault
Executes authenticated operations against the system that owns the capability.
05
Verified result
The skill's completion rules shape the evidence returned to the user.
Decision guide
How the agent turns a request into the right action.
These routes come directly from the skill instructions. They help the model recognize intent and select a focused tool or workflow instead of improvising across the entire capability surface.
"rotate", "renew", "refresh"?
rotate_credential
"revoke", "disable", "compromised"?
revoke_credential
"audit", "who accessed", "usage"?
audit_credential_access
"list", "what secrets", "available"?
list_credentials / get_credential_metadata
"validate", "scope", "permission"?
validate_secret_scope
Proven workflows
Repeatable sequences for useful outcomes.
A workflow joins several tool calls into a task the user actually recognizes. The skill explains the sequence and the intended result while ADK-Rust streams the agent's progress through the shared runtime.
011-2 calls
Request Secret
Scope check → deliver with TTL
021 calls
Rotate
Generate new → verify → retire old
031 calls
Revoke
Immediate invalidation
041 calls
Audit
Access log by credential/time
Tool boundary
The skill may use 8 documented tools.
This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-credentials-vault retains responsibility for authentication, validation, and the connected system.
list_credentials
get_credential_metadata
request_runtime_secret
request_workload_token
rotate_credential
revoke_credential
audit_credential_access
validate_secret_scope
Working rules
What the agent should do.
- Specify purpose/context when requesting secrets
- Respect TTL — don't cache beyond expiry
- Rotate on schedule, not just when compromised
- Audit all access for compliance
Operating boundaries
What the agent should avoid.
- NEVER log or display credential values in plain text
- NEVER cache secrets beyond their TTL
- Don't request broader scope than needed
- Don't skip audit trail
Install and connect
Add the skill beside the capability it expects.
Install the repository where your ADK-Rust skill loader can discover it, connect mcp-credentials-vault, and confirm the declared tools are available before asking the agent to use the workflow.
Install the skill
git clone https://github.com/zavora-ai/skill-credentials-management.git \
~/.skills/skills/credentials-managementADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("credentials-management").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-credentials-vault server connected.
Official documentation
Read the complete skill package.
The repository remains authoritative for its exact instructions, examples, helper scripts, assets, MCP requirements, license, and later updates.
Keep exploring
More in agent infrastructure.
A2A Agent OrchestrationMulti-agent coordination — discover capabilities, dispatch tasks, stream results, and manage remote agent lifecycles via the A2A protocol.10 allowed toolsACP Workspace ManagementCoding agent workspace control — start sessions, delegate tasks to coding agents, review proposed patches, manage permissions, and publish agents with governance gates.9 allowed toolsArtifact LifecycleGoverned artifact management — versioned storage, provenance tracking, integrity verification, derivation chains, and export packaging for build outputs and documents.10 allowed tools
Source record
Repository metadata for this skill entry.
- License
- Apache-2.0
- Allowed tools
- 8
- References
- 3
- Revision
- f6e91eee0584
- Updated
- May 31, 2026