convert-plaintext-to-md
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform local file system operations using shell commands such as 'cp' or 'copy' to initialize markdown files from plaintext sources.
- [EXTERNAL_DOWNLOADS]: The skill fetches markdown syntax and style guidelines from trusted organizations and well-known services, including GitHub's writing guidelines, Microsoft Learn, and the Markdown Guide.
- [PROMPT_INJECTION]: The skill processes untrusted document content, which serves as a potential vector for indirect prompt injection.
- Ingestion points: External files are loaded into the context via the '#file' and '#guide' parameters.
- Boundary markers: The skill does not implement specific delimiters or instructions to ignore embedded commands within the ingested content.
- Capability inventory: The agent has the capability to write to the local file system and fetch content from remote URLs.
- Sanitization: There is no validation or filtering mentioned to prevent the agent from executing instructions found within the documents being converted.
Audit Metadata