meanest-editor
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied content (pitches and press releases) as its primary function.
- Ingestion points: The skill ingests user input in the form of pitch drafts or press releases as mentioned in the frontmatter and instructions.
- Boundary markers: The instructions do not implement specific delimiters to separate user data from the instruction context, though the structured output format provides some logical separation.
- Capability inventory: The skill's capabilities are limited to generating text responses. It does not perform file writes, network requests, or shell command executions.
- Sanitization: No explicit sanitization or escaping mechanisms for external content are defined in the instructions.
- [SAFE]: The skill does not contain any malicious code, obfuscation, or unauthorized access attempts. All instructions are focused on the intended purpose of providing editorial feedback.
Audit Metadata