frontend-review-ci
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
scripts/audit-ci.shwhich is part of the skill package to perform CI auditing. Evidence:scripts/audit-ci.sh --repo <client-repo>inSKILL.md. - [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to retrieve workflow run logs for bottleneck analysis. Evidence:gh run view <run-id> --log | grep -E '^\\d{4}-' | head -200inSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from GitHub logs and local JSON reports, creating a surface where malicious instructions embedded in logs could influence the agent's reasoning. Ingestion points:
gh run viewoutput and<client-repo>/.frontend-review/report/latest/raw/ci.jsoninSKILL.md. Boundary markers: None present. Capability inventory: Shell command execution (gh,scripts/audit-ci.sh), file system access, and report generation. Sanitization: No explicit sanitization of log content is mentioned.
Audit Metadata