frontend-review-security
Warn
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands and local scripts.
- Runs
scripts/audit-security.shto perform an automated security scan of the target repository. - Executes
git logto search through repository history for sensitive files like.envthat may have been committed. - [DATA_EXFILTRATION]: The skill identifies and accesses sensitive configuration files.
- Accesses
.envfiles within the target repository to check for secrets exposure. - Analyzes client-side bundles and environment variable prefixes (e.g.,
VITE_,NEXT_PUBLIC_) to ensure secrets are not leaked to the frontend. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted code and data from external repositories.
- Ingestion points: Reads source code (TSX, JS, HTML), configuration files, and
raw/security.jsonfrom the audited repository. - Boundary markers: There are no instructions for the agent to use delimiters or ignore instructions found within the audited files.
- Capability inventory: The skill can execute shell commands (
git log,audit-security.sh), read any file in the project, and write report files to the filesystem. - Sanitization: The skill does not describe any validation or sanitization process for the data ingested from the external repository.
Audit Metadata