The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration logic detected.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool for local operations and automation. No high-risk, privileged (sudo), or obfuscated command strings were identified in the instructions.
[DATA_EXFILTRATION]: The skill is designed to process sensitive payroll and compensation information. While no exfiltration commands are present, the skill explicitly requests users to provide existing employee data, including names, roles, and total cash compensation. This sensitive data enters the agent's context as part of the intended primary purpose of the skill.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it fetches external data via WebFetch and WebSearch and reads from local documentation.
Ingestion points: External market data from web searches/fetches and the local docs/output-kit.md file.
Boundary markers: Absent; there are no specific delimiters or instructions for the agent to ignore embedded commands within the fetched data.
Capability inventory: Bash (shell access), WebFetch (network access), and Read (file system access).
Sanitization: Absent; the skill does not explicitly describe validation or sanitization of external content before processing.

folk-comp