product-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository, creating a potential attack surface for indirect prompt injection.
- Ingestion points: According to SKILL.md, the agent reads the
README,package.json, landing pages, marketing copy, and other documentation files during the auto-drafting workflow. - Boundary markers: Absent. The instructions do not direct the agent to use delimiters or to ignore instructions that might be embedded within the project files it reads.
- Capability inventory: The risk is mitigated by the skill's limited capabilities; it only reads project files and writes the final document to
.agents/product-marketing.md. It lacks network access, subprocess execution, and access to sensitive system credentials. - Sanitization: The workflow does not include steps to sanitize or validate the content retrieved from external project files before processing.
Audit Metadata