Audit PsychSift source metadata, citations, approvals, labels, provenance, rendering, and release-governance coverage. Use for citation defects, source-governance changes, document labels, public promotion, or clinical evidence traceability.
86%
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 traces ingested source metadata (titles, citations, labels, provenance) that may originate from external publications, but the skill names no outsider submission path, so exposure is at most a selected-document read, which I'm scoring as low under the recall-first override.
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.