build
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security concerns identified. The skill defines a constrained workflow for implementing small code changes based on local project documentation and follows best practices for task scoping.
- [INDIRECT_PROMPT_INJECTION]: The skill reads project-level documentation, which represents a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The skill explicitly reads PROJECT.md and AGENTS.md.
- Boundary markers: The skill includes a 'Boundaries' section that limits the agent's scope, such as instructions not to expand scope or make unauthorized architectural choices.
- Capability inventory: The agent is tasked with implementing code changes, which involves file system write operations.
- Sanitization: No specific sanitization or validation of the input documentation content is defined within the skill instructions.
Audit Metadata