content-strategy

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to perform sales data analysis. It uses standard platform tool connectors (e.g., ~~accounting and ~~payments) or manual CSV file uploads to retrieve data, with no evidence of unauthorized network or file system access.- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it ingests data from external sources. Evidence Chain: 1. Ingestion points: SKILL.md (Step 3: CSV/Excel uploads, accounting and payment APIs). 2. Boundary markers: Absent. 3. Capability inventory: The skill produces a text-based brief and structured JSON for subsequent tools; it lacks high-risk capabilities like shell execution or file-system writing. 4. Sanitization: No explicit validation or sanitization is mentioned. Mitigation: The skill mandates user review and confirmation (Step 6) of the generated brief before it is processed further, significantly lowering the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 01:59 AM
Security Audit — agent-trust-hub — content-strategy