running-integration-tests
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands through a restricted Bash tool to manage Docker containers (e.g.,
docker-compose -f docker-compose.test.yml up -d) and run various test suites. These operations are confined to the tool's allowed scope. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests and processes external data such as SQL seed files and test execution logs.
- Ingestion points: Ingestion occurs via the
test_data.sqlasset file and the output of executed test scripts. - Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: Capabilities include file system modifications (Write, Edit) and scoped shell command execution (Bash) as listed in the
SKILL.mdfrontmatter. - Sanitization: No specific sanitization or validation protocols for the external test data are mentioned in the instructions.
Audit Metadata