product-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data from the repository to generate marketing context.
- Ingestion points: The agent is instructed to read various files within the codebase, including
README, landing pages, marketing copy, andpackage.json, as described in the 'Workflow' section ofSKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its primary instructions and the data being read from the repository.
- Capability inventory: The skill performs file system writes to
.agents/product-marketing.mdacross multiple scripts and steps. - Sanitization: The skill does not implement validation, escaping, or filtering of the content extracted from the repository before using it to generate the final document.
Audit Metadata