Maps keyword clusters to existing website assets and recommends reuse, improvement, consolidation review or a new page.
76%
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 ./skills/keyword-mapping/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 opens candidate pages from the user's own sitemap, navigation, or crawl of their live site to verify them, which can surface third-party text such as comments or reviews, but the agent must select and fetch those pages, so this is low rather than medium.
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's instruction to use the linked site-structure-inventory skill at a GitHub URL is an operational inbound dependency because the agent would load that skill's instructions, and the repository belongs to an individual maintainer, so it is unofficial with no concrete warning sign, placing it in the medium tier.
kostja94/marketing-skills
ac823a1
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.