translator
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied content for translation, which is a common vector for indirect prompt injection attacks. Malicious instructions could be embedded in the source text to influence the agent's behavior during the translation process.
- Ingestion points: User-provided source text for translation within the prompt structure defined in SKILL.md.
- Boundary markers: Absent. The skill does not define specific delimiters or instructions to treat the input as pure data and ignore any embedded directives.
- Capability inventory: The skill is a persona-based agent and does not request high-risk tool permissions such as file writing, network access, or command execution in its YAML frontmatter.
- Sanitization: There is no logic provided to sanitize or validate the input text for potential injection patterns.
Audit Metadata