outreach-auditor

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill reads and writes to local files specifically within the .sales/ directory (.sales/context.md, .sales/outreach/results.md). This file access is limited to its stated purpose of outreach auditing and does not involve sensitive system files.
  • [PROMPT_INJECTION]: The skill processes untrusted user-provided content such as pasted emails and DMs. This is a surface for indirect prompt injection, but the risk is minimized as the skill has no network or shell execution capabilities.
  • Ingestion points: User-pasted outreach communications (emails, DMs, call notes) in step 1.
  • Boundary markers: None present to distinguish untrusted content from instructions.
  • Capability inventory: Limited to file writing (.sales/outreach/results.md).
  • Sanitization: No evidence of input validation or sanitization before processing text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 06:11 PM
Security Audit — agent-trust-hub — outreach-auditor