Use when working with error debugging multi agent review
43%
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/error-debugging-multi-agent-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 workflow reads the user-supplied target at `$ARGUMENTS` (file paths, Git repositories, or snippets), so a Git repository the user points to could contain outsider-authored comments or docs that the agent ingests only after the user selects that target, which fits the selected-source "low" category.
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.