sales-coaching

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to process untrusted data from external sources.
  • Ingestion points: In SKILL.md (Step 1), the skill is instructed to collect reply_text from email campaigns and transcript from call recordings, which are provided by external prospects.
  • Boundary markers: The instructions do not include specific boundary markers (e.g., XML tags or delimiters) or explicit 'ignore embedded instructions' warnings for the data being analyzed.
  • Capability inventory: The skill uses capabilities for data analysis and reporting (data-analysis, call-analysis, email-analysis, reporting). It does not appear to utilize dangerous capabilities like arbitrary shell command execution or direct network exfiltration.
  • Sanitization: There is no mention of sanitizing or escaping the content of email replies or transcripts before they are processed by the model for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:17 PM