Dialogflow Cx Agents

PassAudited by ClawScan on May 10, 2026.

Overview

This appears to be a straightforward Dialogflow CX management skill, but it uses Google Cloud credentials and includes update/delete actions that should be confirmed carefully.

Install only if you intend to let the agent manage Dialogflow CX agents in your Google Cloud project. Use limited credentials, verify project/location/agent names before updates or deletes, and install the required Google Python packages from a trusted source.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If broad Google Cloud credentials are used, the skill can act across any Dialogflow resources those credentials can access.

Why it was flagged

The skill requires Google Cloud credentials that can authorize Dialogflow CX API actions. This is expected for the purpose, but the credential scope controls what projects and agents can be read or modified.

Skill content
- Service account or OAuth credentials with Dialogflow API access
- `gcloud` CLI authenticated OR bearer token
Recommendation

Use least-privilege credentials limited to the intended project and Dialogflow actions, and avoid using broad owner/admin credentials.

What this means

Running the wrong delete command could remove a Dialogflow CX agent from a Google Cloud project.

Why it was flagged

The CLI exposes a direct delete operation for Dialogflow agents. This is aligned with the stated purpose, but the code does not add an extra confirmation before deletion.

Skill content
def delete_agent(agent_name: str):
    client = AgentsClient()
    
    client.delete_agent(name=agent_name)
Recommendation

Confirm the full agent resource name and project/location before update or delete operations, and consider backing up/exporting important agents first.

What this means

Dependency installation depends on the user's Python package source and current package versions.

Why it was flagged

The script requires external Python packages installed manually and does not pin package versions. These are standard Google libraries and purpose-aligned, but the install provenance is left to the user.

Skill content
Install:
    pip install google-cloud-dialogflow-cx google-auth
Recommendation

Install dependencies from trusted package indexes and consider pinning versions in a controlled environment.