renovate-maintainer
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run the official Renovate configuration validator and perform local dependency extraction to verify changes.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted configuration data from repositories, which presents a surface for indirect prompt injection if the configuration files contain malicious instructions.
- Ingestion points: Reads repository configuration files (e.g.,
.github/renovate.json), inherited presets, and version declarations (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or "ignore previous instructions" warnings when processing the content of these files.
- Capability inventory: The skill possesses the ability to read and modify repository files and execute shell commands for validation and extraction (SKILL.md).
- Sanitization: No explicit sanitization or content validation steps are defined for the input configuration data beyond the use of standard validation tools.
Audit Metadata