test-anti-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, which inherently introduces a vulnerability surface.
- Ingestion points: The
Inputssection inSKILL.mdexplicitly lists 'Test code' and 'Production code' as data provided by the user for processing. - Boundary markers: The skill workflow does not instruct the agent to use delimiters or 'ignore embedded instructions' warnings when reading and analyzing the content of these external files.
- Capability inventory: The skill is restricted to file-reading and analysis; it does not request high-risk capabilities such as network access, file-writing, or shell command execution in its instructions.
- Sanitization: There are no instructions provided for sanitizing or validating the content of the ingested code files before they are processed by the agent.
Audit Metadata