The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for the AI to follow when analyzing business offers. It does not include any scripts, commands, or network operations.
[NO_CODE]: No executable files, scripts (Python, Node.js, Shell), or configuration files that trigger code execution are present.
[DATA_EXPOSURE_&_EXFILTRATION]: There are no network requests, hardcoded credentials, or attempts to access sensitive system files. All operations are restricted to processing the input text provided by the user.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data such as OFFER.md or product descriptions. While it lacks explicit boundary markers for this untrusted data, the skill possesses no dangerous capabilities (like shell execution or network access) that an attacker could leverage via injection.

value-accelerator