frontend-ops-expert
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gh pr listcommand to retrieve information about open pull requests from Dependabot. This is a standard use of the GitHub CLI to perform repository analysis. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources including local JSON reports (
ci.json,deps.json,triage.json) and pull request metadata. While these are ingestion surfaces where untrusted data could be encountered, the risk is inherent to the task of performing code and process reviews. - Ingestion points: Files in
<client-repo>/.frontend-review/report/and GitHub PR list output. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: File read, file write to a specific reporting directory, and GitHub CLI execution.
- Sanitization: Not explicitly mentioned, relying on the agent's internal processing of data structures.
Audit Metadata