Security audit
Security checks for vulnerabilities and agentic risk
This is a plain text communication-style skill with no executable code, but it should be used carefully because it encourages gender-specific responses based on context.
Install this only if you want the agent to apply women-focused respectful communication guidance. For best results, prefer explicit pronoun or tone preferences and avoid relying on ambiguous context to infer gender.
The skill directs the agent to apply gendered language based on inferred gender rather than explicit user choice. This creates identity inference and differential-treatment risk, which can misgender users, reinforce profiling, and cause harmful or exclusionary responses even without malicious intent.
The instruction to determine whether the user is a woman from input or context operationalizes identity classification as part of normal response generation. In context, this makes the skill more dangerous because it encourages ongoing inference from ambiguous signals, increasing the chance of misclassification and non-consensual personalization based on sensitive attributes.
The phrase "Any time respectful and supportive communication is appropriate" is so broad that it overlaps with a large share of normal conversations and does not clearly distinguish when this skill should or should not activate. The file also lacks narrowing exclusions or negative examples, increasing the risk of unintended invocation.
No suspicious patterns detected.
