app-marketing-context
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a central repository for app marketing context by reading from and writing to
app-marketing-context.md. This creates a surface where data provided by the user (or existing in the file) could influence the behavior of this or other agent skills that reference the document. - Ingestion points: Reads the file
app-marketing-context.mdfrom the project root or.claude/directory. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested text.
- Capability inventory: The skill has the ability to read and write markdown files to the local file system.
- Sanitization: No explicit validation or sanitization is performed on the user-provided answers before they are saved to the document.
Audit Metadata