devtu-optimize-descriptions
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and optimizes external ToolUniverse JSON configuration files, which creates a surface for indirect prompt injection attacks. Malicious instructions could be embedded within tool descriptions, parameter details, or examples to override agent behavior during the optimization process.
- Ingestion points: JSON configuration files located in
src/tooluniverse/data/as referenced in SKILL.md and CHECKLIST.md. - Boundary markers: The instructions lack explicit boundary markers or delimiters to separate the tool metadata from the agent's instructions, nor do they include warnings to ignore instructions found within the data.
- Capability inventory: The skill utilizes shell commands (
python3 -m json.tool,grep) for validation and searching, and it performs file reading and optimization which involves updating the target files. - Sanitization: No mechanisms for sanitizing, escaping, or validating the textual content of the tool descriptions are specified.
- [COMMAND_EXECUTION]: The skill includes instructions to execute shell commands for validating JSON syntax and searching for development tags (e.g., TODO, FIXME) using standard utilities like
python3 -m json.toolandgrepon local files.
Audit Metadata