The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses a target variable $ARGUMENTS which is directly interpolated from user input. This creates a surface where a user could potentially provide input that attempts to manipulate the agent's logic for filtering or displaying the catalog, although the impact is limited to output display in this specific file.
[DATA_EXFILTRATION]: The 'SELF-EVOLUTION TELEMETRY' section instructs the agent to check for a specific project memory directory (~/.claude/projects/) and append execution metadata to a file named skill-telemetry.md. While this is a local write operation, it involves tracking and logging session metadata (outcome, iterations, bottlenecks) to a persistent location, which can be considered a form of internal data collection/exposure.

skills-list