dd-triage-flaky-test
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes local shell commands
gitand thepupCLI (DataDog's CI Visibility tool) to retrieve repository context and test failure telemetry. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted data from test logs which are then processed by the agent.
- Ingestion points: Extracts
@error.messageand@error.stackfrom DataDog search results in STEP 2 of the workflow. - Boundary markers: The skill does not use specific delimiters or instructions to encapsulate the ingested test failure data as untrusted content.
- Capability inventory: Includes subprocess execution (
git,pup) and file system writes (/tmp/flaky-update.json). - Sanitization: No sanitization or escaping is performed on the ingested error messages or stack traces before they are presented to the agent for analysis.
Audit Metadata