test
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files to determine its testing logic and execution parameters.
- Ingestion points: The skill reads
.cocoplus/lifecycle/spec.mdto extract success criteria and deliverables. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard or isolate potential instructions embedded within the specification files.
- Capability inventory: The agent has access to powerful tools including
SnowflakeSqlExecutefor database operations,Bashfor system command execution, and the ability to modify local files and perform Git commits. - Sanitization: The skill does not describe any validation or sanitization process for the content extracted from the specification files before using it to generate test cases or executable commands.
- [COMMAND_EXECUTION]: The skill is designed to execute SQL queries and Bash commands based on its interpretation of the project specification. This capability is part of the intended functionality but represents a significant control surface that could be exploited if the input data is manipulated.
Audit Metadata