The Agent Skills Directory

[PROMPT_INJECTION]: The skill directly interpolates user-provided $ARGUMENTS into the primary instructional prompt. This creates a surface for direct prompt injection where a user could provide input designed to override the agent's investigator persona or instructions.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection.
Ingestion points: External ticket data fetched from Gorgias via GORGIAS_GET_TICKET and GORGIAS_LIST_TICKETS in SKILL.md.
Boundary markers: None. The skill instructs the agent to analyze the data directly without delimiters or instructions to ignore embedded commands.
Capability inventory: The agent has access to the Bash tool to execute composio CLI commands, which can perform various platform actions.
Sanitization: None. The ticket content is processed as raw text for pattern recognition and the 'Five Whys' framework.
[COMMAND_EXECUTION]: The skill uses shell commands (composio search, composio execute) to interact with the Gorgias API via the Composio platform. These commands are standard for the skill's stated purpose and are managed through the Composio CLI environment.

root-cause