testing-standard
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and act upon instructions found in external repository files, which represents an attack surface for indirect prompt injection. \n- Ingestion points: AGENTS.md, TESTING_STANDARD.md, build/package configuration files, and CI workflows. \n- Boundary markers: The skill does not define specific delimiters to separate untrusted repository content from the agent's internal instructions. \n- Capability inventory: The skill directs the agent to execute shell commands for formatting, linting, building, and running test suites as documented in the repository. \n- Sanitization: There are no explicit instructions to sanitize or validate the content of the repository files before processing or execution.
Audit Metadata