skills/sjunepark/agent-scripts/record/Gen Agent Trust Hub

record

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Git commands including git rev-parse, git check-ignore, and git ls-files to manage file visibility and ensure the record file is not included in version control history.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it reads and reconciles state from an external file (RECORD.md).
  • Ingestion points: Reads from RECORD.md at the repository root or a user-specified path.
  • Boundary markers: The record uses a standard markdown template but lacks specific security delimiters to segregate untrusted content.
  • Capability inventory: The skill can read/write to the file system and execute Git commands via the shell.
  • Sanitization: The instructions include a mitigation strategy requiring the agent to represent sensitive values by their purpose rather than their literal content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 10:09 AM
Security Audit — agent-trust-hub — record