The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to automatically modify several user shell profile files to append environment variable exports for tool persistence.
Affected files: ~/.profile, ~/.bashrc, ~/.bash_profile, ~/.zshrc, ~/.zprofile.
Action: Appends export PATH="$HOME/.local/bin:$HOME/.local/analyticscli-npm/bin:$PATH" to each file.
[PROMPT_INJECTION]: The skill retrieves and processes product analytics and feedback data from an external API, introducing a surface for indirect prompt injection where malicious data could influence agent behavior.
Ingestion points: Output from analyticscli commands like funnel, timeseries, and feedback list.
Boundary markers: Absent; instructions do not specify delimiters to separate data from instructions.
Capability inventory: The agent has the ability to execute shell commands and modify local startup scripts.
Sanitization: No sanitization or verification of the external data is described.
[EXTERNAL_DOWNLOADS]: The skill installs software from external registries that is associated with the skill author.
Package: @analyticscli/cli via NPM.
Source: wotaso/analyticscli-skills repository via NPX.

analyticscli-cli