product-marketing-context
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process untrusted data from the repository, creating a vulnerability surface where malicious instructions in project files could influence the agent's output.
- Ingestion points: The skill instructions explicitly direct the agent to read
README,package.json, landing pages, and marketing copy from the local environment (defined inSKILL.md). - Boundary markers: There are no defined delimiters or instructions to treat external file content as untrusted data or to ignore embedded commands.
- Capability inventory: The skill involves reading project files and writing to a persistent configuration file at
.claude/product-marketing-context.mdwhich is intended to be used by other downstream skills. - Sanitization: No sanitization, validation, or filtering of the content read from the codebase is performed before it is drafted into the context document.
Audit Metadata