The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to execute various agent-almanac CLI commands via the Bash tool. These commands are used for project framework detection, content discovery, and installation processes.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of external agentic components (skills, agents, and teams) from registries into the local development environment.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and installs external instructions and prompts from potentially untrusted or third-party registries.
Ingestion points: External content enters the agent's context through the project manifest (agent-almanac.yml) and registry files managed by the CLI.
Boundary markers: The procedure does not describe the use of specific boundary markers or delimiters to isolate the agent from instructions embedded within the installed content.
Capability inventory: The skill has permissions to execute Bash commands and perform file writes to various framework-specific directories (e.g., .claude/skills/).
Sanitization: There is no mention of sanitization or validation of the content being installed to ensure it does not contain malicious instructions.

install-almanac-content