mp-layout
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted user content (Markdown, plain text, or existing HTML) to perform rewriting and structural changes. While the conversion script uses
html.escapeto sanitize the final output, the lack of explicit boundary markers or delimiters between the user's data and the agent's instructions could allow malicious text within a draft to influence the agent's behavior during the editing phase. - [COMMAND_EXECUTION]: The skill instructs the agent to execute a locally provided Python script,
scripts/md2mp.py, to convert content to HTML. This execution is central to the skill's primary purpose and uses a zero-dependency script included in the distribution, representing normal functional behavior.
Audit Metadata