onboarding-cro
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read an external context file to personalize recommendations, which is a potential surface for indirect prompt injection if the file content is untrusted.
- Ingestion points: Reads
.claude/product-marketing-context.md(identified inSKILL.md). - Boundary markers: None identified; instructions do not include delimiters or warnings to ignore embedded instructions in the context file.
- Capability inventory: The skill provides strategy and advice; it does not explicitly call for dangerous subprocesses, file writes, or network operations.
- Sanitization: No validation or sanitization of the input file content is specified.
- [NO_CODE]: The skill consists entirely of Markdown instructions and reference documentation. It does not include executable scripts, binary files, or external package dependencies.
Audit Metadata