Reference-only CrossFrame archive with a local evidence-review fallback; upstream suite execution and source-fidelity certification are unavailable.
57%
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
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/crossframe-review/SKILL.mdThe 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 local evidence-review path reads user-supplied output and "any source actually supplied" (which may include outsider-authored web or news material the user selects), but the workflow never searches or fetches on its own and no feed or queue is monitored.
BigSimmo/Communication
b4de79a
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.