content-strategy
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, code obfuscation, or remote code execution were found in the skill instructions or associated files.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from various research sources. 1. Ingestion points: Research data from sales transcripts, survey responses, and web research results (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: The skill reads local context files (.agents/product-marketing-context.md) and performs web searches (SKILL.md). 4. Sanitization: Absent. This risk is inherent to the research task and is categorized as safe because the skill processes this data solely for strategy formulation without executing it in a privileged or dangerous context.
Audit Metadata