skills/sharadchaturveda-coder/agency-agents-codex/agency-behavioral-nudge-engine/Gen Agent Trust Hub
agency-behavioral-nudge-engine
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to the way it processes external data.
- Ingestion points: The skill ingests untrusted data from the user's task queue during Phase 2 of the workflow and the task title interpolation in the example code.
- Boundary markers: No delimiters or instructions are provided to distinguish between the task content and the system instructions, increasing the risk that a task title could contain overriding commands.
- Capability inventory: The skill generates actionable messages for communication channels like SMS and Email, which could be used to deliver malicious content if the input data is compromised.
- Sanitization: There is no requirement or evidence of sanitization or validation of task data before it is used to generate notifications.
Audit Metadata