xcodebuildmcp-snapshot-fixture-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review data from project files and a documentation URL (
xcodebuildmcp.com/app/docs/_content/testing.mdx). While this represents a surface for indirect prompt injection where malicious instructions could be hidden in the processed data, the risk is minimized by the skill's restricted scope. - Ingestion points: Specified in
SKILL.mdunder the 'Files to inspect' section, covering fixture files, contract code, and a documentation URL. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the inspected files.
- Capability inventory: The skill is strictly limited to review and analysis; it does not contain or request capabilities for file writing, network exfiltration, or command execution.
- Sanitization: No sanitization or validation mechanisms for the ingested data are mentioned.
- [SAFE]: The skill establishes benign developer-focused guardrails for maintaining the integrity of snapshot tests and JSON contracts. It does not exhibit patterns of obfuscation, privilege escalation, or persistence.
Audit Metadata