sales-retargeting

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill instructions and reference materials are focused on providing marketing consultation and strategy.
  • [PROMPT_INJECTION]: The skill employs a persistence mechanism by reading and writing to a local learnings file (references/learnings.md). This represents a minor surface for indirect prompt injection, though the impact is negligible due to the consultative nature of the skill and lack of privileged capabilities. 1. Ingestion points: references/learnings.md. 2. Boundary markers: Absent. 3. Capability inventory: Local file write operations. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 03:59 PM