coder-modules
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill leverages repository-local scripts, such as
./scripts/new_module.sh, and standard development utilities includingbunandterraformto manage scaffolding, validation, and testing workflows for Coder modules. - [INDIRECT_PROMPT_INJECTION]: The skill's instructions require the agent to ingest and analyze external tool documentation and existing module source code from the Coder Registry. This represents an attack surface for indirect prompt injection if external content contains malicious instructions designed to influence the agent's code generation.
- Ingestion points: External documentation URLs and Coder Registry module sources accessed via
registry.coder.com. - Boundary markers: None specified for the interpolation of external data into prompts.
- Capability inventory: Shell script execution (scaffolding and testing) and repository file modification.
- Sanitization: No explicit sanitization or filtering of external data is defined in the instructions.
Audit Metadata