shots-translate
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external, user-supplied text such as benefit headlines, subtitles, and ASO metadata to perform translations and regenerate screenshots. This creates a surface for indirect prompt injection where an attacker could place instructions in the metadata to manipulate the agent's behavior.
- Ingestion points: App Store benefit headlines, subtitles, and ASO metadata described in the skill's purpose.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined in the provided instruction file.
- Capability inventory: The skill allows the use of potentially high-risk tools including
Bash(node),Bash(npm),Bash(curl), andBash(open). - Sanitization: There is no evidence of sanitization or input validation for the metadata being processed.
Audit Metadata