code-quality
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow where the agent is instructed to find and execute tasks specified in
AGENT_TODOtags within code comments. This constitutes an indirect prompt injection surface.\n - Ingestion points: The agent ingests and processes source code files from the repository during tasks like refactoring, editing, and reviewing (
SKILL.md).\n - Boundary markers: Absent. The instructions in
references/important-tags-and-doc-generation.mdexplicitly command the agent to follow these tags as indicators of things it "should do" without specifying a priority over safety guidelines or providing markers to isolate the comment content.\n - Capability inventory: The agent possesses capabilities to modify repository files, generate new code, and provide detailed explanations of its actions (
SKILL.md).\n - Sanitization: No validation or sanitization process is described for the content extracted from the
AGENT_TODOtags before the agent incorporates those instructions into its workflow.
Audit Metadata