Review the current PsychSift diff, branch, or explicitly approved PR target for high-confidence correctness, security, privacy, clinical, and reliability defects. Use for code review, diff review, or readiness feedback.
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads PR comments on the reviewed pull request (step 1, to find a `Review record`), and PR comments can be posted by outside users without the agent selecting a specific item, so this is medium under the GitHub PR-reading rule.
BigSimmo/PsychSift
fada614
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.