The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data returned from the mom status command, creating a potential vector for indirect instructions if the tool output is manipulated.
Ingestion points: The agent reads and processes the output of the mom status command as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters to wrap the tool output, though it does instruct the agent to summarize rather than print raw output.
Capability inventory: The skill utilizes the Bash tool to execute status and setup commands.
Sanitization: The instructions explicitly require the agent to redact sensitive fields such as keys, tokens, and passwords using [REDACTED] and to summarize the output, which significantly mitigates the risk of data exposure.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the mom CLI tool from a remote repository via Homebrew.
Evidence: It suggests the command brew install momhq/tap/mom and references the source at https://github.com/momhq/mom. The resource belongs to the skill's vendor and the instructions explicitly forbid installation without user consent.
[COMMAND_EXECUTION]: The skill relies on shell commands to manage its environment and query its state.
Evidence: Uses command -v mom for path verification and mom status for operational reporting.

mom-status