improve-test-cases
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external markdown files that may contain instructions disguised as data.
- Ingestion points: Reads markdown files (
.md,.test.md) from common test directories or the whole project (SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested test files.
- Capability inventory: The skill performs file system read and write operations, including overwriting existing files (SKILL.md).
- Sanitization: There is no evidence of sanitization or validation of the input content to prevent the execution of embedded instructions.
Audit Metadata