The Agent Skills Directory

[SAFE]: No malicious patterns, command executions, or data exfiltration techniques were detected in the skill instructions or evaluation files.
[DATA_EXPOSURE]: The skill mentions reading a local context file (.agents/product-marketing-context.md). This is a standard practice for retrieving project-specific information and does not involve accessing sensitive system credentials or private keys.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local context file. While this represents a theoretical ingestion point for untrusted data, the skill possesses no dangerous capabilities (such as network access or shell execution) that could be exploited via this vector.

popup-cro