adk-deployment-specialist
Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. Use when asked to "deploy ADK agent" or "orchestrate agents". Trigger with phrases like 'deploy', 'infrastructure', or 'CI/CD'.
63
56%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/ai-ml/jeremy-adk-orchestrator/skills/adk-deployment-specialist/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and parses AgentCard and A2A task responses from arbitrary deployed agent endpoints (e.g., validating `/.well-known/agent-card` and POSTing to `/tasks/send` as shown in SKILL.md step 5, references/how-it-works.py discover_agent/send_task examples, and scripts/test-a2a-protocol.py), meaning untrusted third-party agent-provided JSON is read and used to drive discovery and subsequent actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). The test script (scripts/test-a2a-protocol.py) makes runtime HTTP calls to a user-supplied agent URL (e.g., https://my-agent-xyz.run.app) — fetching /.well-known/agent-card and POSTing JSON‑RPC tasks to /tasks/send — which will cause the remote agent to execute tasks/logic, so contacting arbitrary external agent endpoints at runtime can directly trigger remote code execution or control agent behavior.
- Commit
3a2d27d
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.