audience-building

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data (prospect imports and pasted blocks) which could contain malicious instructions designed to influence the agent's behavior during the data processing phase.
  • Ingestion points: Prospect data is ingested from files, exports, or manual pastes as described in SKILL.md (lines 14 and 72).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' commands to isolate untrusted data from the agent's instructional context.
  • Capability inventory: The skill utilizes bulk write operations including contact.create and contact.update (SKILL.md, line 33).
  • Sanitization: The skill focuses on data quality validation (e.g., email reachability) but does not include patterns for sanitizing or escaping content to prevent instruction injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 06:47 PM
Security Audit — agent-trust-hub — audience-building