coderabbit-rate-limits
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
gh(GitHub CLI) andcurlcommands to query rate limits and fetch repository data. These actions are within the expected scope for review automation and API monitoring.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the GitHub API, including pull request titles and review metadata. This provides a potential vector for indirect prompt injection if the repository contains malicious content designed to influence the agent.\n - Ingestion points: Data enters the context via
gh apiandgh api graphqlcalls within the provided bash scripts.\n - Boundary markers: No delimiters or instructions to ignore embedded content are used in the prompt interpolation.\n
- Capability inventory: The skill has access to
Bash(gh:*),Bash(curl:*), andWritetools across its instructions.\n - Sanitization: The scripts use
jqfor parsing JSON fields, which ensures basic structural validity but does not filter content for prompt injection patterns.
Audit Metadata