css-modules
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests configuration data from external files such as .agents/css-modules.json and repository instructions to determine which commands to run. This creates an attack surface where a malicious project configuration could influence agent behavior.
- Ingestion points: The skill reads .agents/css-modules.json and repository-level instructions as described in SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between its own logic and potentially malicious instructions embedded in the project configuration.
- Capability inventory: The skill is authorized to execute several shell commands defined in the project profile, including css:generate, css:types, css:check, and css:verify.
- Sanitization: The skill does not specify any validation or sanitization for the command strings retrieved from the project configuration before execution.
- [COMMAND_EXECUTION]: The skill utilizes shell command execution to perform project-specific tasks. The specific commands are dynamically determined by the project profile, which represents a capability that relies on the integrity of the local environment.
Audit Metadata