sequence-load

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external sources, specifically Gmail drafts and HTML reports, which are then used to drive actions in Apollo and HubSpot. This creates a surface for indirect prompt injection if the source data contains malicious instructions.
  • Ingestion points: Data is read from Gmail drafts and HTML reports in Stage 1.
  • Boundary markers: There are no explicit delimiters or safety instructions provided to the agent to treat the ingested data as untrusted content.
  • Capability inventory: The skill possesses significant capabilities including creating contacts and enrolling them in outreach sequences in Apollo, as well as creating or modifying records in HubSpot via the manage_crm_objects tool.
  • Sanitization: The skill performs basic validation of data formats (email, phone) but lacks content sanitization to prevent the execution of instructions embedded within the processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 06:50 PM