unblock-pr
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands to gather context and perform actions. It executes
gitcommands (git remote get-url,git symbolic-ref) to determine the repository and branch. It also uses theghCLI for retrying GitHub Actions runs and thepupCLI for interacting with Datadog APIs. - [PROMPT_INJECTION]: The skill processes data from external CI pipeline and test events (e.g., error messages, job names, and URLs) to classify failures and automate responses.
- Ingestion points: Tool outputs from
search_datadog_ci_pipeline_eventsandsearch_datadog_test_eventsin STEP 1. - Boundary markers: None explicitly defined for processing event data.
- Capability inventory: Execution of shell commands (
gh run rerun) and tool calls (retry_datadog_ci_job,update_datadog_flaky_test_states). - Sanitization: Employs extraction patterns for IDs from URLs, which provides structural validation of the input.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the
pupCLI from the author's official distribution channel (brew install datadog-labs/pack/pup).
Audit Metadata