Navigate unfamiliar code using GitNexus knowledge graph
62
73%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./gitnexus-cursor-integration/skills/gitnexus-exploring/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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 reads from `gitnexus://repo/{name}/context` and `gitnexus://repo/{name}/process/{name}`, which at runtime will pull in free-text codebase-derived content from repositories the operating user did not author, creating an indirect prompt-injection risk via that fetched external repository text.
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 skill issues runtime READ requests to gitnexus:// URLs (e.g., gitnexus://repo/{name}/context) which will fetch external repository context that directly feeds the agent's prompts/context and is required for the skill to function.
c6b2416
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.