The Agent Skills Directory

[SAFE]: The skill follows secure patterns for analyzing local project data. It does not perform network operations, file modifications, or execute arbitrary code.
[DATA_EXPOSURE]: The skill accesses local configuration files (e.g., .acumen.md, .acumen/personas.md) to provide grounded analysis. This access is restricted to the local file system and is necessary for the skill's primary function of product critique.
[PROMPT_INJECTION]: The skill processes untrusted user input (product artifacts) as a primary function. While this presents a surface for indirect prompt injection, the skill lacks the capabilities (such as network access or shell execution) to allow an attacker to exploit this entry point.

critique-product