product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository to automatically generate marketing drafts, creating a potential surface for indirect instructions.
- Ingestion points: The agent is instructed to read various files within the codebase, including
README.md,package.json, landing pages, and marketing copy (specified in SKILL.md Step 2). - Boundary markers: The instructions lack explicit delimiters or safety warnings to ignore natural language instructions that might be embedded within the files being studied.
- Capability inventory: The skill performs file system read operations across the repository and write operations to the
.claude/directory. - Sanitization: There are no documented procedures for sanitizing, escaping, or filtering the content retrieved from external files before the agent processes it for the draft.
Audit Metadata