product-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes a codebase scanning feature to ingest data from README files, landing pages, marketing copy, and package.json to auto-draft marketing context. This creates an inherent surface for indirect prompt injection if those files contain adversarial instructions designed to influence the agent's behavior.
- Ingestion points: Reads various local repository files such as
README,package.json, and marketing materials specified inSKILL.md. - Boundary markers: None identified; the instructions do not include specific delimiters or warnings to ignore instructions embedded within source project files.
- Capability inventory: The skill is scoped to reading project files and writing a structured markdown document to
.agents/product-marketing.md. - Sanitization: The skill does not explicitly sanitize or validate the content gathered from the repository before drafting the output document.
Audit Metadata