nooks-followup-stager
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted transcript data from external sources to generate email drafts, creating a potential vector for malicious instructions to influence the agent.
- Ingestion points: Transcripts and notes provided by users or fetched via APIs such as
clari_get_callandgetCall(referenced in SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions to the agent to ignore or isolate instructions that might be embedded within the transcripts.
- Capability inventory: The skill has the capability to write to the user's environment using the
create_draft(Gmail) andhubspot_create_contact_note(HubSpot) tools. - Sanitization: There is no evidence of sanitization, filtering, or escaping of the transcript content before it is processed for email generation.
Audit Metadata