product-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it is designed to ingest and process data from the local repository (such as README files and marketing copy) to automatically generate marketing drafts.
- Ingestion points: Scans local codebase files including README, landing pages, marketing copy, and package.json during the 'Auto-draft' workflow (Step 2).
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious embedded commands when reading these external files.
- Capability inventory: The skill utilizes file reading capabilities to scan the repository and file writing capabilities to create or update the
.agents/product-marketing.mdfile. - Sanitization: There is no explicit sanitization or filtering of the ingested repository content before it is processed by the agent to draft sections.
Audit Metadata