pr-review-ci-fix
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides instructions to install the Composio CLI tool by downloading and executing a shell script from the author's official domain (
https://composio.dev/install). - [COMMAND_EXECUTION]: The skill makes extensive use of the
composioCLI to manage authentication (composio login), search for toolkits, and execute API-driven actions for GitHub and GitLab. It also performs local shell operations for code patching and version control (git commit,git push). - [EXTERNAL_DOWNLOADS]: The skill fetches external data from GitHub and GitLab, including pull request metadata, file content, and CI workflow logs, which are used for automated code analysis and debugging.
- [PROMPT_INJECTION]: The skill's primary function involves processing external, potentially untrusted data from PR files and logs, which creates a surface for indirect prompt injection.
- Ingestion points: Pull request diffs and CI logs are ingested via tools like
GITHUB_LIST_PULL_REQUESTS_FILESandGITHUB_DOWNLOAD_WORKFLOW_RUN_LOGS. - Boundary markers: The instructions do not specify any boundary markers or delimiters to isolate untrusted external content from the agent's instructions.
- Capability inventory: The agent has the capability to write to the local filesystem, execute code fixes, and push commits to remote repositories.
- Sanitization: No explicit sanitization or validation steps are defined for the logs or diff data before they are processed by the agent.
Audit Metadata