Microsoft Foundry image generation
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is purpose-aligned for Azure Foundry image generation, but it requires an Azure API key and sends prompts to the configured endpoint.
Before installing, confirm you want your agent to call Azure Foundry, use your own trusted HTTPS endpoint, provide a scoped API key, and monitor Azure quota or costs. The reviewed artifacts do not show hidden installation, persistence, or unrelated data access.
Findings (2)
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.
Prompts are sent to the configured Azure Foundry deployment, and generated outputs are written locally under /tmp.
The skill uses local CLI tools to POST an image prompt to the configured Azure endpoint and write the response. This is disclosed and central to the stated purpose, but it is still a networked tool action users should recognize.
jq -n --arg prompt "$PROMPT" ... | curl --fail --show-error --silent --url "$url" ... --data-binary @- -o /tmp/generation_result.json
Use a trusted Azure endpoint, review prompts before sending them, and move or delete generated files from /tmp as appropriate.
Anyone or any agent action using this key may consume Azure Foundry quota or access deployments permitted by that key.
The skill requires and transmits an Azure Foundry API key to authenticate image-generation requests. This is expected for the integration, but the key can authorize use of the user's Azure resource and quota.
export FOUNDRY_API_KEY="<your_api_key>" ... -H "api-key: ${FOUNDRY_API_KEY}"Use a scoped key for the intended deployment, keep it out of logs and shared files, rotate it if exposed, and ensure FOUNDRY_ENDPOINT is a trusted HTTPS Azure endpoint.