test-generator
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: A comprehensive security audit detected no malicious patterns. The skill's tools and operations are appropriate for its stated purpose of software testing.
- [PROMPT_INJECTION]: The vulnerability surface for indirect prompt injection was evaluated. Ingestion points: source code files are accessed using the 'Read' tool. Boundary markers: the skill logic does not utilize specific delimiters to isolate untrusted code. Capability inventory: the skill is permitted to use 'Write', 'Edit', 'Grep', and 'Glob' tools. Sanitization: no content filtering is applied to the input source code. Despite the presence of this ingestion surface, the risk is classified as safe because the operations are confined to the local project and lack the network or privilege capabilities required for significant impact.
Audit Metadata