orbitant-blog-post-translate
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, user-supplied content (Spanish blog posts) which represents a potential attack surface for indirect prompt injection. A malicious article could theoretically contain hidden instructions that attempt to manipulate the agent's behavior during the translation process.
- Ingestion points: The skill accepts a 'validated Spanish blog post' as the primary input for processing.
- Boundary markers: There are no explicit boundary markers or delimiters defined to separate the input content from the skill's instructions.
- Capability inventory: The skill is restricted to text generation (Markdown output) and does not possess capabilities for file system modification, network requests, or command execution.
- Sanitization: The instructions do not specify any validation or sanitization routines for the input text beyond checking if it appears to be a finished article.
Audit Metadata