end-of-day-cleanup

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Git command-line interface to manage vault versioning and synchronization. Evidence includes instructions to execute git status, git pull --rebase origin main, git commit, and git push origin main within the /Vault directory.
  • [DATA_EXFILTRATION]: The Git workflow involves pushing the contents of the local Obsidian vault to a remote server. Evidence is the use of git push origin main to synchronize files (including daily notes and backlog files) to the remote repository. This is an intended part of the skill's synchronization feature.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes user-controlled data.
  • Ingestion points: The skill reads content from Daily/<today>.md, Daily/backlog.md, and Templates/Daily Note Template.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the workflow to separate user data from agent instructions.
  • Capability inventory: The skill has the ability to write to the file system, move content between files, and perform Git push operations.
  • Sanitization: No sanitization or validation of the note content is performed before the agent processes it to determine task completion or movement.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 04:01 PM
Security Audit — agent-trust-hub — end-of-day-cleanup