tdd
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read a local
CONTEXT.mdfile to synchronize its understanding with the project's domain language and requirements. - Ingestion points:
CONTEXT.md(referenced inSKILL.md). - Boundary markers: The skill does not define specific delimiters or "ignore embedded instructions" warnings for the content processed from
CONTEXT.md. - Capability inventory: The agent is granted the capability to generate and modify code (implementations and tests) based on the instructions retrieved from the context file.
- Sanitization: No explicit sanitization, filtering, or validation of the context file's content is specified before interpolation into the agent's prompt.
- [EXTERNAL_DOWNLOADS]: The skill provides installation instructions that utilize the
skillsCLI tool from a public repository and references a GitHub repository for content synchronization and updates.
Audit Metadata