sales-coaching

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of external, untrusted content.
  • Ingestion points: The skill ingests prospect email replies and call transcripts as defined in the Step 1 data collection matrix in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between the system instructions and the potentially untrusted data being analyzed.
  • Capability inventory: The skill utilizes data-analysis and reporting capabilities and passes processed data to downstream skills such as email-drafting, creating a path for injected instructions to influence future outgoing communication.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the ingested email or call content before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 06:25 PM
Security Audit — agent-trust-hub — sales-coaching