merge-renovate-pull-requests
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and interpret pull request descriptions and external repository changelogs to understand breaking changes and migration paths. Since this content is sourced from external contributors or potentially compromised dependencies, it presents an indirect prompt injection risk where an attacker could embed malicious instructions to influence the agent's behavior during the maintenance workflow.
- Ingestion points: Pull request descriptions and GitHub repository changelogs (referenced in SKILL.md).
- Boundary markers: None identified. The instructions do not define delimiters or warnings for the agent to ignore embedded commands within the external text.
- Capability inventory: The agent has access to the GitHub CLI (gh), git operations (merging, branching, pushing), file system modification (tsconfig.json, AGENT_MERGE.md, .vscode/settings.json), and the ability to execute shell commands such as 'pnpm install', linting, and build scripts.
- Sanitization: No validation, escaping, or sanitization of the external content is required or described before the agent processes it.
Audit Metadata