referrals
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed exclusively of markdown documentation and strategic marketing guides. There are no scripts (Python, JavaScript, etc.) or binary files included.
- [SAFE]: No network operations, exfiltration patterns, or attempts to access sensitive system files or credentials were detected.
- [PROMPT_INJECTION]: The skill contains an ingestion surface for indirect prompt injection by reading local project context files.
- Ingestion points: Reads
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.md(SKILL.md). - Boundary markers: No explicit delimiter or security warning is provided for these files.
- Capability inventory: No dangerous capabilities are present; the skill lacks subprocess execution, file-writing, or network access tools.
- Sanitization: The ingested data is used solely to provide contextual marketing advice within the conversational session.
Audit Metadata