The Agent Skills Directory

[PROMPT_INJECTION]: Potential for indirect prompt injection through external data ingestion. The skill analyzes existing email content which could contain malicious instructions intended to manipulate the agent's output or behavior.
Ingestion points: The skill reads content from the references/examples/emails/ directory for analysis.
Boundary markers: No delimiters or specific instructions to ignore embedded commands within analyzed data are provided.
Capability inventory: The agent possesses Bash execution capabilities and file system access via Read, Write, Glob, and Grep tools.
Sanitization: There is no documented validation or sanitization of the input data before it is processed by the analysis scripts.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Python scripts, specifically scripts/content/analyze_emails.py and scripts/content/write_email.py. While these scripts are part of the skill's intended functionality, executing local code based on potentially untrusted input (the analyzed emails) carries an inherent risk.

email-copywriter