fec-validation-fix
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill identifies and executes commands defined in the project's
package.jsonor repository documentation, including lint, type-check, unit/integration tests, and build scripts. This is the primary intended function for verifying code changes. - [PROMPT_INJECTION]: The skill ingests untrusted data from command outputs and project source files, which creates a surface for indirect prompt injection.
- Ingestion points: The agent reads stdout/stderr from validation commands and contents of project files like
package.jsonor source code. - Boundary markers: No explicit delimiters are specified to isolate untrusted command output from the agent's logic.
- Capability inventory: The agent can execute arbitrary shell commands defined in the repository and write report files to the
reports/directory. - Sanitization: The skill does not mention any sanitization or validation of command output or file content before the agent evaluates it for repair actions.
Audit Metadata