structural-review
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied markdown drafts, creating an ingestion point for untrusted data.
- Ingestion points: Input consists of draft markdown provided by the user.
- Boundary markers: The instructions do not define specific delimiters for separating the draft content from the skill's logic.
- Capability inventory: The skill is limited to text analysis and generating feedback sections. No subprocess calls, network access, or file-write operations are defined or requested in the frontmatter.
- Sanitization: No explicit sanitization of the input markdown is performed before processing.
- [SAFE]: The skill implements standard text processing logic for editorial review. No evidence of obfuscation, credential harvesting, remote code execution, or persistence mechanisms was found. The instructions remain focused on the stated goal of structural editing.
Audit Metadata