implement
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes verification commands, typechecking, and test suites as defined in project configuration files.
- Evidence: The instructions direct the agent to run "verification commands" from
.agent/context/loops.mdand execute the "full test suite" to verify implementation work. - [INDIRECT_PROMPT_INJECTION]: The skill processes external inputs such as PRDs and issue descriptions, which represents a surface for indirect prompt injection attacks.
- Ingestion points: Processes PRD and issue content provided by the user or extracted from the repository.
- Boundary markers: Lacks explicit delimiters or instructions to ignore potentially malicious embedded commands in the source data.
- Capability inventory: The agent can execute shell commands for testing and verification, and has permissions to commit changes to the repository.
- Sanitization: The skill does not define specific sanitization or filtering logic for the data it processes.
Audit Metadata