Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward IRB drafting helper that writes generated documents locally and does not show hidden network, credential, persistence, or destructive behavior.
Before installing, treat this as a drafting aid rather than IRB approval, review all generated content against your institution's requirements, and be aware that generated IRB text is saved locally to the output path.
The activation text is broad enough to trigger on general research-ethics or human-subjects mentions, even when the user is not clearly requesting IRB application assistance. This can cause inappropriate skill routing, exposing unrelated conversations or causing the agent to produce compliance-oriented outputs in the wrong context.
The activation summary 'Use when working with irb application assistant' is circular and too vague to constrain when the skill should be invoked. In a sensitive IRB/compliance context, overly broad routing can cause the skill to activate for loosely related research, ethics, or compliance queries, increasing the chance of inappropriate handling of regulated human-subjects content or user overreliance on the wrong workflow.
The manifest frames the skill as an assistant for drafting informed consent documents, reviewing protocols, generating application forms, and preparing checklists. In code, the tool also persists the generated content to disk by default, which is additional behavior beyond the described assistance functions rather than an obvious requirement of the manifest wording.
