daily
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from various files and tools to generate summaries, which creates an attack surface for instructions embedded in those data sources to influence agent behavior. * Ingestion points: The skill reads from context/priorities.md, decisions/log.md, the projects/ directory, and the output of the tools/open_loops.py script. * Boundary markers: The instructions do not define boundary markers to distinguish between system instructions and data ingested from external files. * Capability inventory: The skill is capable of pulling data from calendar, task, and CRM MCP connections. * Sanitization: No sanitization or validation of the ingested data is specified before it is processed by the agent.
- [DYNAMIC_EXECUTION]: The skill references and executes a local Python script to retrieve commitment data. * Path: tools/open_loops.py * Method: Execution of a local script file to provide data.
Audit Metadata