game-localization-manager
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit and process strings and code from external, untrusted sources which could contain malicious instructions. \n
- Ingestion points: The agent is instructed to read through entire codebases using Read, Glob, and Grep tools to identify localization issues in the Audit the codebase workflow step. \n
- Boundary markers: There are no instructions provided to separate the audited content from the agent's internal logic, nor are there commands to ignore instructions embedded in the data. \n
- Capability inventory: The skill has access to the Write, Edit, and Bash tools, which could be exploited if the agent erroneously executes instructions found in the codebase. \n
- Sanitization: The skill does not implement or recommend any sanitization or validation of the data ingested from the project files.
Audit Metadata