The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown instructions for data analysis and report formatting. It does not include any executable scripts, binary files, or automated shell commands.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted external data, such as customer interview notes and online reviews. While this creates an attack surface for indirect prompt injection, the skill lacks any high-risk capabilities (such as network access, file system writes, or code execution) that could be leveraged for a malicious exploit. The instructions also explicitly require the agent to cite source IDs for all information, which provides a layer of human-verifiable provenance.
[SAFE]: No evidence of data exfiltration, hardcoded credentials, or obfuscated content was found. The reference to the author's personal website is consistent with the provided author identity and represents a standard vendor resource.

customer-intelligence