guard-activate-onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted content from multiple sources, creating a potential surface for indirect prompt injection.
- Ingestion points:
references/input-rules.md(Rule 1 and Rule 5) explicitly directs the agent to accept and normalize content from 'conversational dumps', Slack pastes, PDF slides, and meeting transcripts. - Boundary markers: The instructions do not specify the use of delimiters or provide guardrails to prevent the agent from following malicious instructions hidden within user-provided data.
- Capability inventory: The skill's capabilities are limited to generating structured text output (Success Plans and Status Updates) within the chat interface. It does not perform file system writes, network requests, or subprocess executions.
- Sanitization: No sanitization or validation logic is defined for the input data before it is processed by the model.
Audit Metadata