flaky-smoke-tests
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [Command Execution]: The skill utilizes common command-line tools, including the Azure CLI, Git, and Node.js, to interact with build pipelines and validate source code locally. These operations are standard for the skill's stated diagnostic purpose.
- [External Downloads]: The skill retrieves build logs and artifacts from a well-known development service. These network operations are used to fetch telemetry and failure details for analysis within the agent's context.
- [Indirect Prompt Injection]: The skill ingest and processes external data from automated build logs and test runner outputs.
- Ingestion points: Data enters the context via Azure CLI commands and artifact downloads described in sections 2, 3, and 4 of SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands were identified in the processing steps.
- Capability inventory: The skill possesses the capability to execute shell commands (
az,git,npm,node) and perform file system operations. - Sanitization: No explicit sanitization or filtering of the retrieved log content was identified.
Audit Metadata