First-party app · A2A Agent Call
a2a-action
Hand one task to an external A2A agent when a trigger fires. Reaches only hosts the operator has allow-listed under Settings › Security › Network egress.
Before you install
A first-party app of PersonalClaw v0.3.9
No scan on record before install
PersonalClaw publishes no scan of its own apps before you install one.
PersonalClaw runs its own scan of the actual code of every app it installs: this one is rescanned when you install, and that scan is what can stop an install.
Its row on Compare: install rescan
- Compatibility
- Works with PersonalClaw v0.3.9
What it gets
- Permissions
- network: true
- Its own network permission
- On. Its own network permission is a declaration, not a fence.
What it reaches
- Hosts it names
- Not declared in this release's manifest
Its own code has no host list at this release: any hosts it names are for the programs, servers and sources it starts or fetches, not everything it can reach. Its own network permission is a declaration, not a fence.
Secrets you would enter
- Settings marked secret
- Headers (JSON)
- Agent password
The app's settings file holds only a reference, the value lives in the credential store, and every route that shows settings masks it. The app's own code receives the value when it runs.
Its own code calls PersonalClaw's gateway with a token scoped to the app, not with your owner token.
What installing it gives and runs
The manifest's own declarations, under the names install consent shows them by and in its order. The Store adds, at install, which of them run as you.
- Permissions it is granted
{ "network": true }- Provider modules the gateway loads
[ { "type": "action", "implementation": "provider:create_provider" } ]
Not declared in this release's manifest:
- Scheduled jobs
- Python packages installed for it
- Engine packages it can install
- What it needs that PersonalClaw does not install
- Programs on this machine it starts
- npm packages installed for it
- Places outside its folder it writes
- Pages it adds to the dashboard
- Components it adds to the dashboard
- A server process of its own
- The sandbox tier its server runs in
- Command run after install
- Command run after an update
- Command run when it is switched on
- Command run when it is switched off
- Command run before it is removed
- What it runs for personalclaw setup
- What it runs for personalclaw doctor
- Connector sources it parses
- MCP servers it adds
- Skills it installs
Where it comes from
- Publisher
- PersonalClaw
- License
- MIT
- Pinned commit
- 169cbc4f8fc59cd42a65a6a3546235bc49ab3b22
- Signer
- Not declared in this release's manifest
From review to enable
- Held and scanned. An install stages the app in quarantine, checks its signature, and runs the shared supply-chain scanner over the staged bytes before anything is shown for consent. A registry's recorded verdict is not read at install: the scan that can stop it is this one.Its row on Compare: install rescan
- A dangerous verdict ends it. A dangerous verdict returns a refusal before consent is asked, so there is no consent to give and no switch that skips it. A warning verdict asks for your consent instead.Its row on Compare: dangerous verdict
- You review and consent. The review records a digest of the staged bytes, and an install committed against different bytes is refused: it needs consent again, because the app changed after it was reviewed. An update that changes what the app gets asks for consent again too.Its row on Compare: consent
- Its setup runs, then you switch it on. Nothing it declares runs before your consent; an app already installed is offered as an update instead.
To install it and switch it on
- In PersonalClaw, open the Store.
- Find a2a-action.
- Review what it gets and runs, and consent.
- Install it, then switch it on.
Evidence
a2a-action/app.json at the pinned commit, as written, with the blob hash git lists for it: c459cc4f229d9a47a9d676a96a18f5e7cdf4f958
{
"name": "a2a-action",
"version": "0.1.3",
"displayName": "A2A Agent Call",
"description": "Hand one task to an external A2A agent when a trigger fires. Reaches only hosts the operator has allow-listed under Settings › Security › Network egress.",
"icon": "Share2",
"author": "PersonalClaw",
"license": "MIT",
"tags": [
"action"
],
"permissions": {
"network": true
},
"provider": {
"id": "action",
"label": "Hand a task to an A2A agent",
"type": "action",
"entity": "a2a",
"implementation": "provider:create_provider",
"capabilities": [
"execute"
],
"autonomy": {
"floor": "one_tap",
"ceiling": "one_tap"
},
"settingsSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"x-meta": {
"label": "Agent URL",
"help": "The external agent's A2A tasks endpoint. The host must be listed in Settings › Security › Network egress — egress is deny-by-default, so an unlisted host is refused before any connection is made. Never write a password into the address: an agent that signs in with one takes it in Agent password. A task with a password or headers is sent over https only (plain http only to this machine) and never follows a redirect."
}
},
"skill": {
"type": "string",
"default": "",
"x-meta": {
"label": "Skill",
"help": "The skill id to invoke on the remote agent, as it appears on that agent's card. Leave blank to let the remote agent choose."
}
},
"text": {
"type": "string",
"default": "",
"x-meta": {
"label": "Message",
"help": "The text sent to the agent. Supports $EVENT, $CONTEXT and any key from the trigger payload. Leave blank to send the event name and context."
}
},
"inputs": {
"type": "string",
"default": "",
"x-meta": {
"label": "Inputs (JSON)",
"help": "Optional JSON object of structured inputs for the skill, e.g. {\"since\": \"7d\"}."
}
},
"headers": {
"type": "string",
"default": "",
"x-meta": {
"label": "Headers (JSON)",
"help": "Optional JSON object of extra request headers. In a scheduled or event automation, enter a credential in one as {{secret:NAME}}, a secret saved in Settings → Secrets, e.g. {\"Authorization\": \"Bearer {{secret:MY_TOKEN}}\"} for an agent that takes a bearer token: it is filled in only when the task is sent. A lifecycle hook fills it from PersonalClaw 0.3.5.",
"sensitive": true
}
},
"username": {
"type": "string",
"default": "",
"x-meta": {
"label": "Agent user name",
"help": "For an agent that signs in with a user name and password: the user name. Leave empty for one that takes a bearer token, or nothing."
}
},
"password": {
"type": "string",
"default": "",
"x-meta": {
"label": "Agent password",
"help": "For an agent that signs in with a user name and password: the password, sent as HTTP basic sign-in with Agent user name. In a scheduled or event automation, enter it as {{secret:NAME}}, a secret saved in Settings → Secrets, so it is filled in only when the task is sent. A lifecycle hook fills it from PersonalClaw 0.3.5.",
"sensitive": true
}
}
}
}
}
}
- Scan verdict
- No scan on record before install
- Scan time
- No scan is published before install
- Blocking findings
- No scan is published before install
- Scanner version
- No scan is published before install
PersonalClaw publishes no scan of its own apps before you install one.
Every app is scanned again when you install it, whatever its listing says.
An install stages the app in quarantine, checks its signature, and runs the shared supply-chain scanner over the staged bytes before anything is shown for consent. A registry's recorded verdict is not read at install: the scan that can stop it is this one.
apps/app_manager.py at v0.3.9A dangerous scan verdict stops the install, and nothing overrides it.
A dangerous verdict returns a refusal before consent is asked, so there is no consent to give and no switch that skips it. A warning verdict asks for your consent instead.
apps/app_manager.py at v0.3.9Consent covers exactly what you reviewed, and an app that changed asks again.
The review records a digest of the staged bytes, and an install committed against different bytes is refused: it needs consent again, because the app changed after it was reviewed. An update that changes what the app gets asks for consent again too.
apps/app_manager.py at v0.3.9A setting an app marks secret is kept in the credential store and never shown back.
The app's settings file holds only a reference, the value lives in the credential store, and every route that shows settings masks it. The app's own code receives the value when it runs.
apps/secret_fields.py at v0.3.9
PersonalClaw/PersonalClawApps @ 169cbc4f8fc5 · a2a-action/app.json