product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data and writes the results to files.
- Ingestion points: The workflow instructions specify reading workspace docs (README, changelogs) and researching external web content (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to separate ingested data from its internal instructions.
- Capability inventory: The skill uses file writing tools to update shared context files in
scripts/marketing/. - Sanitization: The skill does not define validation or sanitization steps for content retrieved from external sources before storage.
- [NO_CODE]: The skill package is comprised solely of Markdown instruction files and templates, without any accompanying executable scripts or binaries.
Audit Metadata