testany-trigger
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied arguments and data retrieved from the Testany platform, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: User input via the
$ARGUMENTSvariable and data retrieved from MCP tools (e.g.,testany_get_plan,testany_list_pipelines) are interpolated into the agent's context inSKILL.md. - Boundary markers: No explicit delimiters (like XML tags or triple quotes) or 'ignore embedded instructions' warnings are present to isolate untrusted data from the system prompt or skill instructions.
- Capability inventory: The skill has powerful capabilities, including triggering pipeline executions (
testany_execute_pipeline) and performing CRUD operations on triggers (Plans and Gatekeepers) across workspaces. - Sanitization: There is no evidence of sanitization, validation, or escaping of the external data before it is used to influence the agent's logic or tool parameters.
Audit Metadata