marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Comprehensive analysis of the skill instructions and reference files found no evidence of malicious intent or suspicious behavior.
- [NO_CODE]: This skill is entirely comprised of markdown documentation and does not contain any scripts, binaries, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it reads local context files such as .agents/product-marketing.md (Ingestion point). It lacks boundary markers and sanitization for this data. However, there are no exploitable capabilities (subprocess calls, file-write, or network operations) identified in the skill, which mitigates the risk to the generated marketing advice.
Audit Metadata