product-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses an auto-drafting mechanism that processes local repository content (README, landing pages, marketing copy, package.json) to generate marketing documentation. This behavior introduces a surface for indirect prompt injection.
- Ingestion points: Repository files including README, landing pages, marketing copy, about pages, and package.json as described in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the ingested codebase content.
- Capability inventory: The skill is granted file reading and writing capabilities within the local repository environment as specified in
SKILL.md. - Sanitization: The instructions lack explicit requirements for sanitizing, escaping, or validating the external content before it is interpolated into the drafted document.
Audit Metadata