The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute various chezmoi and git commands to detect drift and sync files. Evidence: Shell commands including chezmoi status, chezmoi diff, and chezmoi git -- push in SKILL.md.
[DATA_EXFILTRATION]: The skill pushes local file changes to a remote git repository, which involves transmitting potentially sensitive dotfile content over the network. Evidence: chezmoi git -- push in SKILL.md.
[CREDENTIALS_UNSAFE]: The skill accesses the chezmoi configuration file, which often contains sensitive environment details or repository URLs. Evidence: Accesses ~/.config/chezmoi/chezmoi.toml as mentioned in the notes.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted file content during the drift check process.
Ingestion points: The agent reads the output of chezmoi diff in Step 1 to identify changes.
Boundary markers: Absent; there are no instructions or delimiters to prevent the agent from following instructions embedded within the file diffs.
Capability inventory: The skill has access to the Bash tool for command execution and the Edit tool for file modification.
Sanitization: Absent; the content of the drifted files is processed directly by the agent without validation or escaping.

chezmoi-sync