marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read local files (e.g.,
.agents/product-marketing.md) to inform its recommendations. This constitutes an indirect prompt injection surface where external data enters the prompt context. - Ingestion points:
SKILL.mdreferences reading.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.mdfor context. - Boundary markers: Absent; the skill does not explicitly instruct the agent to use delimiters or ignore potentially malicious commands within these context files.
- Capability inventory: The skill does not provide any scripts, tools, or binary executables, which minimizes the risk and potential impact of an injection attack.
- Sanitization: None provided for the ingested file content.
- [NO_CODE]: The skill is composed entirely of Markdown instructions, reference documentation, and JSON evaluation files. There are no executable scripts (Python, Node.js, Shell), significantly reducing the potential for runtime malicious activity or privilege escalation.
Audit Metadata