markdown-style
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and provides links to official documentation and style guides, including Google's GitHub-hosted style guide and the Markdown Guide.\n- [NO_CODE]: The skill is entirely composed of documentation and natural language instructions. It does not include any scripts, binaries, or configuration files that execute commands.\n- [PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted Markdown files for review. This ingestion point creates a theoretical surface for indirect prompt injection. However, the risk is minimal given the skill's specific focus on structural styling and the absence of malicious instructions or dangerous capabilities within the skill itself.\n
- Ingestion points: External Markdown documents targeted for review (e.g., README.md, ADR, design docs) as mentioned in SKILL.md.\n
- Boundary markers: None explicitly defined in the instructions to separate data from instructions.\n
- Capability inventory: No tools are restricted in the frontmatter, meaning the agent retains its default toolset while performing the review.\n
- Sanitization: No explicit sanitization or filtering of the input document content is described.
Audit Metadata