trigger-cost-savings
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes live run logs, which represents a potential attack surface for indirect prompt injection if those logs contain malicious instructions.
- Ingestion points: Run logs and status details retrieved via the
get_run_detailstool (SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore instructions embedded within retrieved log data.
- Capability inventory: The skill utilizes MCP tools (
list_runs,get_run_details,get_current_worker) for data retrieval and provides analysis results in markdown format. - Sanitization: There is no evidence of sanitization or filtering for the content of the logs before they are processed by the agent.
- [COMMAND_EXECUTION]: The instructions suggest that the user install the Trigger.dev MCP server using the command
npx trigger.dev@latest install-mcp. This is a standard installation procedure for the vendor's provided tools. - [EXTERNAL_DOWNLOADS]: The skill references documentation and SDK resources from the
@trigger.dev/sdkpackage, which is consistent with the skill's intended functionality.
Audit Metadata