product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local codebase to generate marketing drafts, which could be exploited if those files contain hidden instructions.
- Ingestion points: Reads README, package.json, landing pages, and other repository documentation (
SKILL.md). - Boundary markers: The skill lacks explicit instructions to treat scanned content as data only or to ignore embedded commands.
- Capability inventory: The skill utilizes file system read and write operations (
SKILL.md). - Sanitization: No sanitization or validation of the ingested codebase content is performed before processing.
Audit Metadata