Reviews credentials, token handling, JWT claims, service-role confinement, public error envelopes, Row-Level Security (RLS) policies, and private bucket access. Use during database, authentication, or network boundary edits.
83%
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 includes a PR review that ends with posting a `Review record` comment on the PR, which implies reading GitHub PR content that external contributors can author, so this is treated as medium under the recall-first override even though the skill never explicitly says to read PR descriptions.
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.