Load to add, tune, or debug document byte ceilings and DOC_LIMITS_* settings.
84%
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 measures byte sizes of tracked AGENTS.md/CLAUDE.md/GEMINI.md/SKILL.md files and prints their repository paths in notices, but never reads document content; the only outsider-influenced text is a tracked path name that someone would have to add to the repository first, which the agent does not select.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The only inbound fetch is the README's documented `kendex add vanillagreencom/kendex --skill doc-limits` install path, which pulls installed skill material from a GitHub repository whose publisher is established only as an individual-style project owner, not a recognized first-party organization, so it is a common/reputable unofficial dependency (medium) rather than strong provenance.
vanillagreencom/kendex
3a2f84c
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.