markdown-formatting
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes markdown and MDX files which may contain hidden instructions intended to influence the agent's behavior.
- Ingestion points: The agent reads workspace files using the Read tool and the markdownlint CLI across all .md and .mdx files.
- Boundary markers: There are no instructions or delimiters defined to ensure the agent ignores instructions potentially embedded within the markdown content, such as in HTML comments or metadata.
- Capability inventory: The skill environment provides the agent with access to Bash, Edit, and Read tools, which represent a significant capability set if an injection occurs.
- Sanitization: No content validation or sanitization is performed on the files prior to the agent's analysis or modification of them.
Audit Metadata