product-marketing
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The 'Auto-draft from codebase' feature introduces an attack surface for indirect prompt injection by processing untrusted repository content.\n
- Ingestion points: The skill is instructed to read the
README, landing pages, marketing copy,package.json, and any existing documentation within the codebase to draft the context document (SKILL.md).\n - Boundary markers: The skill instructions do not specify any delimiters or explicit boundary markers to help the agent distinguish between informational content and embedded instructions in the ingested files.\n
- Capability inventory: The skill has the capability to perform repository-wide file reads and write the resulting output to a configuration file at
.agents/product-marketing.md(SKILL.md).\n - Sanitization: There is no requirement or logic provided to sanitize, validate, or filter content extracted from the codebase before it is used to generate the marketing context draft.
Audit Metadata