to-ios-test
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local file system which could contain malicious instructions designed to influence the agent's behavior during the test discovery and selection process.
- Ingestion points: The skill processes user-provided natural language requests in
SKILL.md(Workflow Step 1) to define search scopes and subsequently reads the content of test modules discovered via thergtool (Step 2). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when the agent reads the content of the discovered test files.
- Capability inventory: The skill possesses the ability to discover files using
rg --files, read file contents, and delegate execution to theto-ios-runskill using absolute script paths. - Sanitization: The skill does not describe any validation or sanitization of the content found within the test modules before identifying relevant tests and proceeding with execution.
Audit Metadata