Agentic Advertising: Build Autonomous Media-Buying Agents
v1.3.1Agentic Advertising: Build Autonomous Media-Buying Agents. Build autonomous ad-buying agents: publisher discovery, trust verification, escrow-based ad spend,...
⭐ 0· 93·0 current·0 all-time
by@mirni
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
medium confidencePurpose & Capability
The name and description (build autonomous media-buying agents, escrowed spend, publisher discovery, etc.) align with the SKILL.md content. The guide contains working Python examples that interact with the GreenHelix A2A Commerce Gateway and describes registering agents with cryptographic identities — so requesting an AGENT_SIGNING_KEY is coherent with the stated purpose.
Instruction Scope
This is an instruction-only skill with runnable example code (Python) that targets the GreenHelix sandbox. The instructions reference an agent signing key for request signing and describe network interactions with GreenHelix; they do not appear to instruct the agent to read unrelated files or harvest other credentials. The SKILL.md itself says examples use the GreenHelix sandbox (no API key required) which is consistent with the content.
Install Mechanism
No install spec and no code files are included; nothing will be written to disk by installing this skill. This is the lowest-risk install profile.
Credentials
The skill requires one environment variable, AGENT_SIGNING_KEY, declared as the primary credential. That is proportionate to a guide that demonstrates cryptographic agent identities. However, private signing keys are high-value secrets: storing them in environment variables or supplying a production key to an instruction-only guide carries risk. The skill does not request unrelated credentials.
Persistence & Privilege
always:false and no install or executable code means the skill does not request persistent system presence. The platform default (allowing autonomous model invocation) remains in effect; combined with a signing key this could allow an agent to act autonomously if the agent is run, but that is expected for a guide about autonomous buyers and is not in itself an incoherence.
Assessment
This guide appears coherent for learning and building autonomous ad-buying agents. Before using it: (1) prefer sandbox/testing keys — do not paste production private keys into a tool you haven't audited; (2) review the Python examples yourself before running them and confirm API endpoints are the sandbox URLs; (3) store signing keys in a secure secret manager (not a shared shell env) and limit their scope/permissions; (4) if you plan to run agents autonomously, ensure spend/escrow operations use test accounts or caps and that you understand how the signing key authorizes transactions; (5) if you need higher assurance, ask the publisher for a homepage, documentation, or source repository to audit the examples.Like a lobster shell, security has layers — review code before you run it.
adcpvk9707c0qymxzwkd4wbvtdsrdbh84wfgqadvertisingvk9707c0qymxzwkd4wbvtdsrdbh84wfgqai-agentvk9707c0qymxzwkd4wbvtdsrdbh84wfgqescrowvk9707c0qymxzwkd4wbvtdsrdbh84wfgqgreenhelixvk9707c0qymxzwkd4wbvtdsrdbh84wfgqguidevk9707c0qymxzwkd4wbvtdsrdbh84wfgqlatestvk9707c0qymxzwkd4wbvtdsrdbh84wfgqmedia-buyingvk9707c0qymxzwkd4wbvtdsrdbh84wfgqopenclawvk9707c0qymxzwkd4wbvtdsrdbh84wfgqprogrammaticvk9707c0qymxzwkd4wbvtdsrdbh84wfgqroasvk9707c0qymxzwkd4wbvtdsrdbh84wfgq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
EnvAGENT_SIGNING_KEY
Primary envAGENT_SIGNING_KEY