context-mate
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill executes
git statusto detect uncommitted changes. This is a read-only operation used to trigger recommendations for session wrapping and is part of the intended functionality. - DATA_EXPOSURE (SAFE): The skill reads project metadata files such as
SESSION.md,CLAUDE.md, andPROJECT_BRIEF.md. These are accessed locally to extract project status and no network exfiltration patterns were detected. - INDIRECT_PROMPT_INJECTION (LOW): The skill ingests untrusted data from project files which could potentially contain malicious instructions.
- Ingestion points: Reads
SESSION.mdandPROJECT_BRIEF.md(commands/context-mate.md). - Boundary markers: Absent; the skill extracts content directly into the output template without delimiters.
- Capability inventory: Limited to file system discovery (Glob), file reading, and
git statusexecution. - Sanitization: None detected; the extracted text is interpolated directly into the final report.
Audit Metadata