product-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it scans local codebase files—such as the README, marketing copy, and landing page source—to automatically draft a product marketing context document.
- Ingestion points: codebase scanning (README, landing pages, marketing copy, package.json) as specified in
SKILL.mdduring the auto-draft workflow. - Boundary markers: the instructions do not define specific delimiters or instructions to ignore embedded commands within the scanned codebase files.
- Capability inventory: the skill is capable of reading repository files and writing markdown content to the
.agents/directory. - Sanitization: there is no explicit sanitization or validation mentioned for the content extracted from the codebase before it is used to generate the context draft.
Audit Metadata