team-coaching-rollup
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests call disposition names from Nooks and activity data from HubSpot, which are fields that could be modified by the sales representatives being monitored to influence the agent's coaching output.
- Ingestion points: Data is pulled via Nooks
listCallsandlistCallDispositionstools and the HubSpotrep_activitydataset, as defined in thedata_sourcessection of SKILL.md. - Boundary markers: Absent. The instructions do not define delimiters or specific "ignore" instructions for the ingested external data to prevent the agent from obeying embedded commands.
- Capability inventory: The skill possesses the capability to send Slack messages (
slack_send_message) and write local HTML reports (outputs/team-coaching-rollup-YYYY-MM-DD.html) based on the processed data. - Sanitization: Absent. The workflow does not include instructions for sanitizing or validating the content of the external strings before they are interpolated into the final reports or messages.
Audit Metadata