Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok.
58
61%
Does it follow best practices?
Impact
90%
5.29xAverage score across 1 eval scenario
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/apify-influencer-discovery/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 runtime ingests outsider-authored free text indirectly via the actor’s downloaded dataset items (e.g., scraped bios/posts/comments) and then prints them in “quick answer” mode or writes them to the output file.
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 runtime JS calls Apify API endpoints such as https://api.apify.com/v2/acts/${apiActorId}/runs?token=${encodeURIComponent(token)}, which starts/polls Apify Actors (remote code execution) and is required for the skill to function.
1f67c44
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.