messages-ops
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and process untrusted data from external sources such as DMs, SMS, and other messaging platforms. This data could contain malicious instructions intended to influence the agent's behavior.
- Ingestion points: SKILL.md (Workflow Step 2: 'read the latest inbound'; Workflow Step 3: 'search the recent local message window').
- Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions for the content being read.
- Capability inventory: The skill can read sensitive message content and one-time codes. It can also hand off data to other internal skills such as 'knowledge-ops' (for context storage) and 'lead-intelligence'.
- Sanitization: Absent. There are no instructions provided to validate or sanitize the message content before processing or passing it to other skills.
Audit Metadata