marketing-product-marketing
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or privilege escalation attempts were detected. The skill's operations are confined to reading local project files and writing a marketing context document to the
.agents/directory. - [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface by ingesting untrusted data from the codebase to auto-draft documentation. This is a low-risk surface as the skill lacks exfiltration or execution capabilities.
- Ingestion points: README, landing pages, marketing copy, and package.json (SKILL.md).
- Boundary markers: Absent; instructions do not specify delimiters for external content.
- Capability inventory: Local file system write access to
.agents/product-marketing.md(SKILL.md). - Sanitization: Absent; the skill relies on the agent's default processing of ingested text.
Audit Metadata