Load for research tasks, architectural investigations, and vendor, library, or technology comparisons.
75%
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/deep-research/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 sends the research query to Exa's search API, which returns outsider-authored web page text (summaries, highlights, and body text) that the agent then reads and synthesizes, so this is search-result exposure that the agent triggers but cannot be forced to receive poisoned content from.
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 operational dependency is the README's setup command `kendex add vanillagreencom/kendex --skill deep-research`, which installs skill material from a GitHub repository owned by the skill's author, an individual-owned project without strong first-party provenance, so it is common/reputable unofficial and rated medium; the Exa API call at runtime is outbound and its responses are research data, not adopted instructions or code.
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.