mkt-content-create
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: No malicious patterns, such as direct prompt injection, hardcoded credentials, or data exfiltration, were identified in the skill instructions or reference materials.
- [NO_CODE]: The skill package is composed entirely of Markdown files; no executable scripts, binaries, or configuration files for package managers were found.
- [PROMPT_INJECTION]: The skill architecture ingests data from local artifacts, creating a potential surface for indirect prompt injection. Ingestion points: .agents/mkt/imc-plan.md, .agents/mkt/product-context.md, and .agents/mkt/icp-research.md; Boundary markers: Absent; Capability inventory: File system read/write access and WebSearch; Sanitization: Absent. This is characteristic of context-aware content generation tools and does not indicate malicious intent.
Audit Metadata