sent-messaging
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external messaging services that could contain hidden instructions aimed at influencing the agent's behavior.
- Ingestion points: External message content and lifecycle events are retrieved via the
messages.getandmessages.activities.listtools as described in SKILL.md. - Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" warnings for the data retrieved from external tools.
- Capability inventory: The skill possesses the
messages.sendcapability, which allows the agent to perform actions based on interpreted data. - Sanitization: While the skill mandates masking sensitive recipient identifiers, it does not specify sanitization or validation protocols for the message bodies themselves.
Audit Metadata