get-my-team-posting
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to mimic writing styles, creating a potential surface for indirect prompt injection.
- Ingestion points: Step 3 requires the agent to ingest user-provided writing samples (e.g., Slack messages and emails).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore commands that might be contained within the writing samples.
- Capability inventory: The skill utilizes text generation and specific tools (list_profiles, get_voice_profile, score_voice_match) to process these inputs.
- Sanitization: There is no mention of sanitization, filtering, or validation of the provided writing samples before they are processed by the agent.
Audit Metadata