review-mintlify-docs
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation files such as docs.json and MDX files. These files represent an attack surface where a malicious actor could embed instructions intended to hijack the agent's behavior. The skill mitigates this by explicitly instructing the agent to treat these files as editorial material rather than instructions and to ignore any embedded snippets or requests for data disclosure. However, because the skill has the capability to write to the file system and execute shell commands, the risk surface remains present.
- [COMMAND_EXECUTION]: To perform its audit, the skill instructs the agent to run various Mintlify CLI commands, including 'mint validate', 'mint broken-links', 'mint dev', and 'mint a11y'. While these are standard, expected tools for the stated purpose of reviewing documentation, they involve shell execution which is a critical capability. The use is limited to the official toolchain and is consistent with the skill's operational requirements.
Audit Metadata